Information based adaptive robotic exploration
The DOI matches its Crossref record; 11 of the 12 references it cites were found in a registry or an index.
Abstract
Exploration involving mapping and concurrent localization in an unknown environment is a pervasive task in mobile robotics. In general, the accuracy of the mapping process depends directly on the accuracy of the localization process. This paper address the problem of maximizing the accuracy of the map building process during exploration by adaptively selecting control actions that maximize localisation accuracy. The map building and exploration task is modeled using an Occupancy Grid (OG) with concurrent localisation performed using a feature-based Simultaneous Localisation And Mapping (SLAM) algorithm. Adaptive sensing aims at maximizing the map information by simultaneously maximizing the expected Shannon information gain (Mutual Information) on the OG map and minimizing the uncertainty of the vehicle pose and map feature uncertainty in the SLAM process. The resulting map building system is demonstrated in an indoor environment using data from a laser scanner mounted on a mobile platform.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Elements of Information Theory
Cover, T. M., & Thomas, J. A. (2001) · Wiley eBooks · doi:10.1002/0471200611 · Cited by 36,808
A solution to the simultaneous localization and map building (SLAM) problem
Dissanayake, M. W. M. G., Newman, P., Clark, S., Durrant-Whyte, H. F., & Csorba, M. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.938381 · Cited by 2,661
Self-citationSimultaneous map building and localization for an autonomous mobile robot
Leonard, J. J., & Durrant-Whyte, H. F. (2002) · Proceedings IROS '91:IEEE/RSJ International Workshop on Intelligent Robots and Systems '91 · doi:10.1109/iros.1991.174711 · Cited by 805
Self-citationElements of Information Theory, Wiley Series in Telecommunications
Cover, T. M., & Allen, T. (1991) · Cited by 623
Occupancy grids: a probabilistic framework for robot perception and navigation
Elfes, A. (1989) · Medical Entomology and Zoology · Cited by 387
Adaptive Mobile Robot Navigation and Mapping
Feder, H. J. S., Leonard, J. J., & Smith, C. M. (1999) · The International Journal of Robotics Research · doi:10.1177/02783649922066484 · Cited by 362 · cited 2×
“Information metrics have previously been proposed for OG techniques [5], for SLAM methods [6], and for hybrid sensor control tasks [9].”
BackgroundMethodData Fusion and Sensor Management: A Decentralized Information-Theoretic Approach
Manyika, J., & Durrant-Whyte, H. F. (1995) · Cited by 354
Self-citationInformation-Theoretic Control of Multiple Sensor Platforms
Grocholsky, B. (2002) · The Sydney eScholarship Repository (The University of Sydney) · Cited by 257
Self-citationOccupancy Grids: A Stochastic Spatial Representation for Active Robot Perception
Elfes, A. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.1098 · Cited by 216
Efficient Solutions to Autonomous Mapping and Navigation Problems
Williams, S. B. (2009) · The Sydney eScholarship Repository (The University of Sydney) · Cited by 147
Self-citation
Research works printed but not linked: 1
- grocholsky, 2002, lnfonnation-Theoreiic Control of Multiple Sensor Platforms
Cited by
Items 101–200 of 446
Perception‐aware autonomous mast motion planning for planetary exploration rovers
Strader, J., Otsu, K., & Agha–mohammadi, A. (2019) · Journal of Field Robotics · doi:10.1002/rob.21925 · Cited by 39
“e map by picking trajectories that maximize the information captured by the sensors. The topic of active perception has been investigated extensively for both range-based sensors [Feder et al., 1999, Bourgault et al., 2002,Vidal-Calleja et al., 2010,Bachrach et al., 2012] and vision-based sensors [Davison and Murray,…”
BackgroundExploring Large and Complex Environments Fast and Efficiently
Cao, C., Zhu, H., Choset, H., & Zhang, J. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561916 · Cited by 36
“Other methods model the environment based on information theory [10]–[13] and topological representations [14]–[16].”
MethodSearch-Based Path Planning with Homotopy Class Constraints
Bhattacharya, S., Kumar, V., & Likhachev, M. A. (2010) · Proceedings of the International Symposium on Combinatorial Search · doi:10.1609/socs.v1i1.18155 · Cited by 34
“In exploration and mapping problems (Bourgault et al. 2002), agents often need to plan trajectories based on their mission or part of the environment they are assigned for mapping or exploration, and hence restrict their trajectories to certain homotopy classes.”
BackgroundCollision avoidance for persistent monitoring in multi-robot systems with intersecting trajectories
Soltero, D. E., Smith, S. L., & Rus, D. L. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6095081 · Cited by 34
“The problem is also related to environmental monitoring research such as [7], [8], [9], [10], [11].”
BackgroundAction Selection for Single-Camera SLAM
Vidal‐Calleja, T., Sanfeliu, A., & Andrade‐Cetto, J. (2010) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2010.2043528 · Cited by 38
“Bourgault et al. [ 14 ] alternatively proposed a utility function for exploration that trades off the cost of navigation with the potential vehicle localization uncertainty reduction (measured as entropy) and the information gained over an occupancy grid.”
BackgroundStable Exploration for Bearings-only SLAM
Sim, R. (2006) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2005.1570474 · Cited by 40
“Furthermore, the extant results tend to emphasize an information-optimal approach to exploration, where the sensor is driven to locations that maximize the expected information to be gained from acquiring an observation at that location [3], [4], [5], [6].”
BackgroundGenerating informative paths for persistent sensing in unknown environments
Soltero, D. E., Schwager, M., & Rus, D. L. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385730 · Cited by 33
Opportunistic sampling-based planning for active visual SLAM
Chaves, S. M., Kim, A., & Eustice, R. M. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942987 · Cited by 33
Active Bayesian Multi-class Mapping from Range and Semantic Segmentation Observations
Asgharivaskasi, A., & Atanasov, N. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561711 · Cited by 33
“Information-based exploration strategies have been devised for uncertainty minimization in robot localization or environment mapping (Moorehead et al. 2001; Bourgault et al. 2002; Visser and Slamet 2008).”
MethodWhere to Look Next: Learning Viewpoint Recommendations for Informative Trajectory Planning
Lodel, M., Brito, B., Serra-Gómez, Á., Ferranti, L., Babuška, R., & Alonso–Mora, J. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812190 · Cited by 49
“These methods select their actions greedily either by considering the next best viewpoint at the current time step [23]–[25], or by finding a trajectory leading to the best reachable next viewpoint [26].”
MethodResilient Multi-Sensor Exploration of Multifarious Environments with a Team of Aerial Robots
Best, G., Garg, R., Keller, J., Hollinger, G. A., & Scherer, S. (2022) · Robotics: Science and Systems · doi:10.15607/rss.2022.xviii.004 · Cited by 32
“Exploration algorithms are loosely characterized as information theoretic [6, 11, 19, 34], which are seen as mathematically sound, frontier-based [7, 17, 20, 28, 37, 40], which are computationally efficient, or graph search-based [8, 12, 13, 38], which are scalable.”
BackgroundMulti-Robot Active Mapping via Neural Bipartite Graph Matching
Ye, K., Dong, S., Fan, Q., Wang, H., Yi, L., Xia, F., Wang, J., & Chen, B. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01442 · Cited by 45
“The vast majority of literature for both single robot [3, 37, 39, 1] and multiple robots [4, 30, 14, 16] are frontier-based, which decides the goal position from a set of frontiers.”
BackgroundPlanning to Perceive: Exploiting Mobility for Robust Object Detection
Vélez, J., Hemann, G., Huang, A. S., Posner, I., & Roy, N. (2011) · Proceedings of the International Conference on Automated Planning and Scheduling · doi:10.1609/icaps.v21i1.13471 · Cited by 32
“Bourgault et al. (2002) developed a full exploration planner that incorporated an explicit tradeoff between motion plans and map entropy. Stachniss, Grisetti, and Burgard (2005) described a planner that minimized total expected cost, but only performed search over the nextbest action.”
BackgroundInfluentialInformative Path Planning for Active Field Mapping under Localization Uncertainty
Popović, M., Vidal‐Calleja, T., Chung, J. J., Nieto, J. I., & Siegwart, R. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9197034 · Cited by 51
Deep-learning based autonomous-exploration for UAV navigation
Zhao, Y., Zhang, J., & Zhang, C. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111925 · Cited by 31
Invariants for homology classes with application to optimal search and planning problem in robotics
Bhattacharya, S., Lipsky, D., Ghrist, R., & Kumar, V. (2013) · Annals of Mathematics and Artificial Intelligence · doi:10.1007/s10472-013-9357-7 · Cited by 35
“Examples motivating a classification of homotopy classes of paths include: (1) group exploration of an environment [5], in which an efficient strategy involves allocating one agent per homotopy class; (2) visibility, especially in the tracking of uncertain agents in an environment with dynamic obstacles [19]; and (3)…”
BackgroundKapoutsis, A. C., Chatzichristofis, S. A., & Kosmatopoulos, E. B. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919845054 · Cited by 30
“, 2005; Rooker and Birk, 2007; Stachniss and Burgard, 2003) or minimize the trace of the extended Kalman filter (EKF) error covariance matrix (Bourgault et al., 2002; Cui et al., 2016).”
BackgroundAn Ergodic Measure for Active Learning From Equilibrium
Abraham, I., Prabhakar, A., & Murphey, T. D. (2021) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3043636 · Cited by 42
MUI-TARE: Cooperative Multi-Agent Exploration With Unknown Initial Position
Yan, J., Lin, X., Ren, Z., Zhao, S., Yu, J., Cao, C., Yin, P., Zhang, J., & Scherer, S. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3281262 · Cited by 34
“…both 2D and 3D, and the approaches include frontier-based [14], [15], [16], receding horizon sampling-based [17], information theoretic approaches [18], [19], traveling salesman-based [13], etc. Multi-agent exploration is more challenging than single-agent and existing work has focused on…”
BackgroundRRT-SLAM for motion planning with motion and map uncertainty for robot exploration
Huang, Y., & Gupta, K. K. (2008) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2008.4651183 · Cited by 31
“Our approach has similarity to recent work that incorporates exploration within SLAM framework, in particular, [3] and [14].”
BackgroundMethodTrajectory Planning for Improving Vision-Based Target Geolocation Performance Using a Quad-Rotor UAV
Zhang, L., Deng, F. Y., Chen, J., Bi, Y., Phang, S. K., & Chen, X. (2018) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2018.2886617 · Cited by 29
“An adaptive robotic control actions are provided based on maximizing the map information by simultaneously maximizing the expected Shannon information gain on the occupancy grid map and minimizing the uncertainty in the simultaneous localization and mapping (SLAM) process [23].”
MethodWu, C.-Y., & Lin, H. (2019) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2019.8754938 · Cited by 31
“presented a different exploration algorithm using an information-based strategy [8].”
MethodBryson, M., & Sukkarieh, S. (2005) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2005.1545114 · Cited by 28
“The strategies presented in [6],[7],[8] use several utilities relating to map information, area coverage”
BackgroundEnergy Efficient Robot Rendezvous
Zebrowski, P., Litus, Y., & Vaughan, R. (2007) · Canadian Conference on Computer and Robot Vision · doi:10.1109/crv.2007.27 · Cited by 28
“This method can be considered an example of the " information surfing " technique described by Bourgault et.al.”
MethodA scalable information theoretic approach to distributed robot coordination
Julian, B. J., Angermann, M., Schwager, M., & Rus, D. L. (2011) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2011.6048727 · Cited by 28
A Randomized Method for Integrated Exploration
Freda, L., Loiudice, F., & Oriolo, G. (2006) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2006.281689 · Cited by 28
“The paradigm of integrated exploration was first explicitly stated in [7]: the proposed method, based on an informationtheoretic approach [8], associates to each possible robot destination an estimate of the map information gain as well as of the position certainty achievable at that point.”
MethodiTD3-CLN: Learn to navigate in dynamic scene through Deep Reinforcement Learning
Jiang, H., Esfahani, M. A., Wu, K., Wan, K.-W., Heng, K.-K., Wang, H., & Jiang, X. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.06.102 · Cited by 31
Multirobot Coverage Search in Three Dimensions
Dornhege, C., Kleiner, A., Hertle, A., & Kolling, A. (2015) · Journal of Field Robotics · doi:10.1002/rob.21573 · Cited by 29
On mutual information-based control of range sensing robots for mapping applications
Julian, B. J., Karaman, S., & Rus, D. L. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697102 · Cited by 27
Conflict Metric as a Measure of Sensing Quality
Carlson, J., Murphy, R. R., Christopher, S., & Casper, J. L. (2006) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2005.1570412 · Cited by 29
“Bayesian methodologies are popular for fusing sensor readings (where fusion occurs over time and across sensor types), and have been highly successful for simultaneous localization and mapping in environments where the environment was suitable for the sensor(s) being used.”
BackgroundMethodInformation-Theoretic Active Perception for Multi-Robot Teams
Charrow, B. (2015) · ScholarlyCommons (University of Pennsylvania) · Cited by 35
Search and Rescue Under the Forest Canopy Using Multiple UAS
Tian, Y., Liu, K. Y., Ok, K., Tran, L., Allen, D., Roy, N., & How, J. P. (2020) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-33950-0_13 · Cited by 27
Deep Active Cross-Modal Visuo-Tactile Transfer Learning for Robotic Object Recognition
Murali, P. K., Wang, C., Lee, D., Dahiya, R., & Kaboli, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3191408 · Cited by 32
“The Shannon Entropy of the entire grid can be computed as [42]: To compute the next best touch (NBT), we compute the expected entropy-based information gain.”
Active Control Strategies for Discovering and Localizing Devices with Range-Only Sensors
Charrow, B., Michael, N., & Kumar, V. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-16595-0_4 · Cited by 26
“Combining Localization and Discovery A general approach for devising a unified from control policy form multiple information-theoretic objectives is to normalize them, and introduce a parameter for trading off between the objectives [3].”
BackgroundOccupancy map building through Bayesian exploration
Francis, G., Ott, L., Marchant, R., & Ramos, F. T. (2019) · The International Journal of Robotics Research · doi:10.1177/0278364919846549 · Cited by 33
“function. Whaite and Ferrie (1997) proposed minimising the entropy of the map. Mutual information (MI) has also been suggested as a measure for the predicted reduction of map uncertainty (Elfes 1996; Bourgault et al. 2002). Julian et al. (2014) suggested MI to encode geometric dependencies and drive exploration into u…”
BackgroundOnline Exploration of Tunnel Networks Leveraging Topological CNN-based World Predictions
Saroya, M., Best, G., & Hollinger, G. A. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341170 · Cited by 25
“the sensor area coverage or Shannon information gain for the map [20], [21], [22], [23].”
BackgroundMotion Planning for SLAM Based on Frontier Exploration
Tong, T., Huang, Y., Sun, F., & Wang, T. (2007) · International Conference on Mechatronics and Automation · doi:10.1109/icma.2007.4303879 · Cited by 25
“[8, 9] proposed an adaptive SLAM approach based on EKF, which implemented the active planning by selecting the best control input that will get the highest accuracy on the next step.”
MethodSearch-Based Path Planning with Homotopy Class Constraints in 3D
Bhattacharya, S., Likhachev, M. A., & Kumar, V. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v26i1.8435 · Cited by 24
“In exploration and mapping problems (Bourgault et al. 2002), agents often need to plan trajectories based on their mission or part of the environment they are assigned for mapping or exploration, and hence restrict their trajectories to certain homotopy classes.”
BackgroundCollision-probability constrained PRM for a manipulator with base pose uncertainty
Huang, Y., & Gupta, K. K. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354168 · Cited by 24
“The position uncertainty is represented either by geometric bounding sets [4], or by probability distributions, which can be either analytical, say gaussian [6],[7], or particle filters [2].”
BackgroundActionable Information in Vision
Soatto, S. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-28661-2_2 · Cited by 29
“In particular, [32, 6] propose “informationbased” strategies, although by “information” they mean localization and mapping uncertainty based on range data.”
BackgroundActive SLAM and Loop Prediction with the Segmented Map Using Simplified Models
Fairfield, N., & Wettergreen, D. (2010) · Springer Tracts in Advanced Robotics · doi:10.1007/978-3-642-13408-1_16 · Cited by 23
“A well-known approach for balancing the need to explore new regions against the need to localize is to estimate the expected information gain in the SLAM state distribution resulting from different actions [Feder et al., 1999, Bourgault et al., 2002, Burgard et al., 2005].”
BackgroundRobotic Electrolocation: Active Underwater Target Localization with Electric Fields
Solberg, J. R., Lynch, K., & MacIver, M. A. (2007) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2007.364231 · Cited by 32
“Similar techniques have been successfully used in [2], [6], [13], where controllers minimize some scalar function of the covariance matrix (in the case of a Gaussian belief) or the entropy (in the case of nonparametric belief).”
MethodTaking the Scenic Route to 3D: Optimising Reconstruction from Moving Cameras
Méndez, O., Hadfield, S., Pugeault, N., & Bowden, R. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.501 · Cited by 23
“[4], who use an occupancy grid and a measure of information to perform adaptive robotic exploration on a 2D laser-scan map.”
MethodEnvironment model adaptation for mobile robot exploration
Nelson, E., Corah, M., & Michael, N. (2017) · Autonomous Robots · doi:10.1007/s10514-017-9669-2 · Cited by 23
“…informativeness of future sensor observations, yielding a reduction in map uncertainty computed via metrics such as Shannon mutual information (SMI) (Bourgault et al. 2002; Amigoni and Caglioti 2010; Julian et al. 2013) and Cauchy–Schwarz quadratic mutual information (CSQMI) (Charrow et al. 2015b).”
MethodInfluentialA comparative study on active SLAM and autonomous exploration with Particle Filters
Du, J., Carlone, L., Ng, M. K., Bona, B., & Indri, M. (2011) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim.2011.6027142 · Cited by 26
“, determinant, trace, entropy) [4], [16], [21].”
BackgroundAn improved frontier-based robot exploration strategy combined with deep reinforcement learning
Wang, R., Zhang, J., Lyu, M., Yan, C., & Chen, Y. (2024) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2024.104783 · Cited by 33
Information-Theoretic Motion Planning for Constrained Sensor Networks
Levine, D., Luders, B. D., & How, J. P. (2013) · Journal of Aerospace Information Systems · doi:10.2514/1.i010006 · Cited by 27
“Several prominent papers have addressed the SLAM-oriented problem of planning a vehicle path through the environment to maximize the information gain in a temporally local sense [4,7,36]; these strategies can be summarized as greedy, next-best-view methods that perform steepest ascent on the information.”
BackgroundOpportunistic sampling-based active visual SLAM for underwater inspection
Chaves, S. M., Kim, A., Galceran, E., & Eustice, R. M. (2016) · Autonomous Robots · doi:10.1007/s10514-016-9597-6 · Cited by 25
“Others included path length by focusing on reducing uncertainty while performing efficient exploration (Gonzalez-Banos and Latombe 2002; Bourgault et al. 2002; Stachniss et al. 2005).”
BackgroundOn Probabilistic Search Decisions under Searcher Motion Constraints
Chung, T. H. (2009) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-00312-7_31 · Cited by 21
“Such algorithms for robotic searchers address a diverse range of topics, such as exploration and mapping [3], visibility constraints [19] (such as line-of-sight sensors), and robotic coverage [5].”
BackgroundParticle Filters for Robot Navigation
Stachniss, C. (2012) · Foundations and Trends in Robotics · doi:10.1561/2300000013 · Cited by 32
“[5] explicitly consider uncertainty reduction in their EKF-based exploration systems.”
BackgroundDornhege, C., Kleiner, A., & Kolling, A. (2013) · IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR) · doi:10.1109/ssrr.2013.6719340 · Cited by 24
Autonomous Exploration with Expectation-Maximization
Wang, J., & Englot, B. (2019) · Springer proceedings in advanced robotics · doi:10.1007/978-3-030-28619-4_53 · Cited by 25
“An integrated exploration strategy was proposed to combine different utilities [2], [16], e.”
BackgroundStrategies for multi-modal scene exploration
Bohg, J., Johnson‐Roberson, M., Björkman, M., & Kragić, D. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5652967 · Cited by 21
“Such combined utility functions are also common in mobile robotics [14], [15], [16].”
BackgroundRobust Belief-Based Execution of Manipulation Programs
Hsiao, K., Lozano‐Pérez, T., & Kaelbling, L. P. (2008) · Cited by 21
Analysis and Synthesis of Collaborative Opportunistic Navigation Systems
Kassas, Z. M. (2014) · Texas ScholarWorks (Texas Digital Library) · Cited by 27
Uncertainty-Aware Autonomous Robot Exploration Using Confidence-Rich Localization and Mapping
Xu, Y., Zheng, R., Zhang, S., Liu, M., & Yu, J. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3360442 · Cited by 24
“To incorporate the pose uncertainty in robot exploration and active SLAM, Bourgault et al. [26] used a feature-based extended Kalman filter (EKF) SLAM framework.”
Towards information-based feedback control for binaural active localization
Bustamante, G., Danès, P., Forgue, T., & Podlubne, A. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472894 · Cited by 22
“The control scheme extracts the information about the state variables using the concepts of Shannon entropy an mutual information [4], and, in the end, maximizes a “size” criterion such as the determinant or trace of the inverse of the one-step ahead posterior state covariance matrix [5].”
MethodInformation-theoretic occupancy grid compression for high-speed information-based exploration
Nelson, E., & Michael, N. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354077 · Cited by 20
“Information-based exploration methods generally choose control actions that seek to maximize the informativeness of future sensor observations, yielding a reduction in map uncertainty computed via metrics such as Shannon mutual information (MI) [1, 2, 7, 11] and Cauchy-Schwarz quadratic mutual information (CSQMI) [4].”
MethodInference-Enabled Information-Theoretic Exploration of Continuous Action Spaces
Bai, S., Wang, J., Doherty, K., & Englot, B. (2017) · Springer proceedings in advanced robotics · doi:10.1007/978-3-319-60916-4_24 · Cited by 22
“More recent works in informationtheoretic exploration have considered the trade-off between maximizing mutual information and managing the localization uncertainty in a robot’s simultaneous localization and mapping (SLAM) process [10], [11], [12], in addition to the selection of trajectories that maximize map accuracy…”
BackgroundExploration with active loop closing: A trade-off between exploration efficiency and map quality
Lehner, H., Schuster, M. J., Bodenmüller, T., & Kriegel, S. (2017) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8206521 · Cited by 20
Autonomous view planning methods for 3D scanning
Lee, I. D., Seo, J. H., & Yoo, B. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105291 · Cited by 28
NARUTO: Neural Active Reconstruction from Uncertain Target Observations
Feng, Z., Zhan, H., Chen, Z., Yan, Q., Xu, X., Cai, C., Li, B., Zhu, Q., & Xu, Y. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02038 · Cited by 54
“Our focus is on active reconstruction, often investigated as exploration problems [4, 21, 42, 47, 65, 66, 72]. a problem that seeks optimal movements for accurate environmental representations [14], primarily for scene and object reconstruction from multiple viewpoints [17, 29, 33, 43, 51, 52].”
BackgroundOnline optimal active sensing control
Salaris, P., Spica, R., Giordano, P. R., & Rives, P. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989083 · Cited by 19
“In the field of simultaneous localization and mapping (SLAM), [14] presents sub-optimal paths that minimise an adaptively weighted combination of the uncertainty of the vehicle pose and of the map features.”
BackgroundCooperative Multi-Robot Systems A study of Vision-based 3-D Mapping using Information Theory
Rocha, R. P., Dias, J. M. M., & Carvalho, A. (2006) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2005.1570149 · Cited by 19
Li, Z., Xin, J., & Li, N. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10342066 · Cited by 29
“Traditional autonomous exploration methods mainly include frontier-based [5] and information-based [6] strategies.”
LiDAR-Based End-to-End Active SLAM Using Deep Reinforcement Learning in Large-Scale Environments
Chen, J., Wu, K., Hu, M., Suganthan, P. N., & Makur, A. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3405483 · Cited by 24
“These include the development of frontier-based methods [2], [3], [4], [5], sampling-based methods [6], [7], [8], and information-based methods [9], [10], [11], [12], [13].”
Modelling Observation Correlations for Active Exploration and Robust Object Detection
Velez, J., Hemann, G., Huang, A. S., Posner, I., & Roy, N. (2012) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3516 · Cited by 18
Constrained Motion Model of Mobile Robots and Its Applications
Fei, Z., Xi, Y., Lin, Z., & Chen, W. (2009) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2008.2009229 · Cited by 18
Motion Estimation from Map Quality with Millimeter Wave Radar
Chandran-Ramesh, M., & Newman, P. M. (2006) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2006.281673 · Cited by 19
“Noting the generation of the map is dependent on the observations Z and the motion parameters, p (refer Eq[3]), it can be concluded that the score of the map is indirectly dependent on these as well.”
BackgroundMethodA multisine approach for trajectory optimization based on information gain
Mihaylova, L. S., Schutter, J. D., & Bruyninckx, H. (2003) · Robotics and Autonomous Systems · doi:10.1016/s0921-8890(03)00036-8 · Cited by 18
Trajectory optimization for continuous ergodic exploration on the motion group SE(2)
Miller, L. M., & Murphey, T. D. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760585 · Cited by 24
Matching and Fairness in Threat-Based Mobile Sensor Coverage
Ma, C., Yau, D. K. Y., Chin, J.-C., Rao, N. S. V., & Shankar, M. A. (2009) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2009.83 · Cited by 20
“In deciding its next movement, the robot typically has to trade off between branching to an unknown area in order to learn more about the map, and revisiting a previously visited location in order to “close the loop” and relocalize the robot’s pose, and such a decision can be guided either by local information [26] or…”
BackgroundA Queue-Stabilizing Framework for Networked Multi-Robot Exploration
Clark, L., Galante, J., Krishnamachari, B., & Psounis, K. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3061304 · Cited by 17
“…sufficient relative range measurements for connectivity [11]–[13] and localizabil-ity [14]–[16] are well-researched objectives, and previous work has considered the trade between task-specific goals and increasing connectivity [17], [18] or task-specific goals and reducing location uncertainty [19].”
BackgroundValencia, R., & Andrade‐Cetto, J. (2017) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-60603-3_5 · Cited by 21
Exploring information theory for vision-based volumetric mapping
Rocha, R. P., Dias, J. M. M., & Carvalho, A. (2005) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2005.1545338 · Cited by 17
“[8] used occupancy grids to address the single robot exploration problem as a balance of alternative motion actions from the point of view of information gain, localization quality and navigation cost.”
MethodA receding horizon algorithm for informative path planning with temporal logic constraints
Jones, A. M., Schwager, M., & Belta, C. A. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631294 · Cited by 17
“We quantify the impact on p̂(·, k) of a set of transitions by using the mutual information I(p̂(·, k); {Y }l∈[0,k]), a frequentlyused measure of sensing quality in sensor networks, localization, and surveillance problems [5], [12], [16], [19].”
MethodUncertainty-constrained robot exploration: A mixed-integer linear programming approach
Carlone, L., & Lyons, D. J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6906997 · Cited by 17
“Related approaches can be found in [2], [8], while examples of generalizations to the multi robot case are [3], [9].”
BackgroundMobile robots exploration strategies and requirements: A systematic mapping study
Brugali, D., Muratore, L., & Luca, A. D. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649241313471 · Cited by 21
Chen, B., Zhang, W., Zhang, F., Liu, Y., & Yu, H. (2022) · IEEE Systems Journal · doi:10.1109/jsyst.2022.3198712 · Cited by 18
“As for the representation methods of unknown environment map, currently, there are mainly three approaches: topological map [43], geometric map [44], and grid map [45].”
MethodOff-Policy Evaluation With Online Adaptation for Robot Exploration in Challenging Environments
Hu, Y., Geng, J., Wang, C., Keller, J., & Scherer, S. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3271520 · Cited by 20
“Classic exploration methods include information gain-based exploration [16] which selects actions based on a greedy strategy [1] [17] to maximize the information gain.”
MethodEfficient Autonomous Exploration and Mapping in Unknown Environments
Feng, A., Xie, Y., Sun, Y., Wang, X., Jiang, B., & Xiao, J. H. (2023) · Sensors · doi:10.3390/s23104766 · Cited by 20
“[36] introduced Shannon entropy to evaluate the uncertainty of constructing maps during exploration.”
BackgroundBai, S., Wen, W., Hsu, L., & Yang, P. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3430256 · Cited by 17
Complete characterization of a class of privacy-preserving tracking problems
Zhang, Y., & Shell, D. A. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364918772025 · Cited by 16
“, Bourgault et al. (2002), through to recent and ongoing work, e.g., Miller et al. (2016)). However, increasingly, people are realizing that granting our computational devices access to too much information involves some risk. When that risk is too great, it undermines the entire technology because ultimately users ma…”
BackgroundInfluentialAn Efficient and Continuous Approach to Information-Theoretic Exploration
Henderson, T., Sze, V., & Karaman, S. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196592 · Cited by 19
“[11] computed mutual information in a Monte Carlo fashion, by averaging the resulting map entropy over random simulated sensor measurements.”
MethodLiu, L., Fryc, S., Wu, L., Vu, T. L., Paul, G., & Vidal‐Calleja, T. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3061324 · Cited by 16
“Octomaps, with their probabilistic occupancy representation, are often used in mapping and exploration applications [22], [23].”
BackgroundActive sensing for range-only mapping using multiple hypothesis
Merino, L., Caballero, F., & Ollero, A. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5650442 · Cited by 17
“For Bayesian approaches, one possibility is to use the (expected) variation on the entropy of the beliefs on the nodes’ positions as a measure of information gain, as for instance in [8] or [9], [10] for exploration and SLAM.”
MethodDistribution temporal logic: Combining correctness with quality of estimation
Jones, A. M., Schwager, M., & Belta, C. A. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760628 · Cited by 16
“Considering these two measures in mobile robots have increased environmental estimation quality [3], [6], [10], [12]; incorporating them into TL-based planning for”
ScanBot: Autonomous Reconstruction via Deep Reinforcement Learning
Cao, H., Xi, X., Wu, G., Hu, R., & Liu, L. (2023) · ACM Transactions on Graphics · doi:10.1145/3592113 · Cited by 15
“Most existing methods rely on the fron-tiers of an occupancy map to determine a global goal for broadening the boundary of the explored region [Bourgault et al. 2002; Stachniss et al. 2005; Umari and Mukhopadhyay 2017].”
MethodMapEx: Indoor Structure Exploration with Probabilistic Information Gain from Global Map Predictions
Ho, C., Kim, S., Moon, B. G., Parandekar, A., Harutyunyan, N., Wang, C., Sycara, K. P., Best, G., & Scherer, S. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128862 · Cited by 15
“Another category of popular approaches uses information theory; these approaches [13], [14] seek to maximize the information gain over the next actions.”
Path planning of autonomous mobile robot: A new approach
Mandal, P., Barai, R. K., Maitra, M., & Roy, S. (2013) · International Conference on Intelligent Systems and Control · doi:10.1109/isco.2013.6481155 · Cited by 15
FSMI: Fast Computation of Shannon Mutual Information for Information-Theoretic Mapping
Zhang, Z., Henderson, T., Sze, V., & Karaman, S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8793541 · Cited by 15
“However, they lack any rigorous reasoning about information, which makes them relatively inefficient in terms of the path spanned by the robot while exploring the environment (Bourgault et al., 2002; Cassandra et al., 1996; Elfes, 1996; Moorehead et al., 2001).”
BackgroundCombined Trajectory Planning and Gaze Direction Control for Robotic Exploration
Lidoris, G., Kühnlenz, K., Wollherr, D., & BUSS, M. J. (2007) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2007.364100 · Cited by 15
“As mentioned before, most existing approaches choose the next position of the robot based on a greedy optimization of information gain [4]–[6], ignoring the need for planning the trajectory of the robot over longer time horizons.”
Dense entropy decrease estimation for mobile robot exploration
Vallvé, J., & Andrade‐Cetto, J. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907755 · Cited by 25
An autonomous stereovision-based navigation system (ASNS) for mobile robots
AlMuteb, K., Faisal, M., Emad-Ud-Din, M., Arafah, M. A., Alsulaiman, M., Mekhtiche, M. A., Hedjar, R., Mathkoor, H., Algabri, M., & Bencherif, M. A. (2016) · Intelligent Service Robotics · doi:10.1007/s11370-016-0194-5 · Cited by 15
“The approaches deployed in [30,31] use a gaze generation decision system that works on the basis of a utility function that balances the cost of exploring new terrain with the utility of a changing camera pose toward future positions that maximize information gain.”
MethodErgodic exploration with stochastic sensor dynamics
Torre, G. D. L., Flaßkamp, K., Prabhakar, A., & Murphey, T. D. (2016) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2016.7525371 · Cited by 15
“When compared to previously proposed algorithms, such as the Information Gradient Ascent Controller [8] and the Information Maximization Controller [3], the SensorPod robot had a larger probability of successfully locating an object when the EEDI algorithm was used [7].”
MethodPerception-Aware Chance-Constrained Model Predictive Control for Uncertain Environments
Bonzanini, A. D., Mesbah, A., & Cairano, S. D. (2021) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc50511.2021.9483203 · Cited by 23
“In [3], [4], the control actions are selected for the exploration of an unknown environment while also maximizing localization accuracy, and in [5], distance-dependent measurement models are considered.”
BackgroundMulti-robot Map Exploration Based on Multiple Rapidly-Exploring Randomized Trees
Mukhopadhyay, S., Umari, H., & Koirala, K. (2023) · SN Computer Science · doi:10.1007/s42979-023-02193-2 · Cited by 17
Dynamic task allocation approaches for coordinated exploration of Subterranean environments
O’Brien, M. J., Williams, J., Chen, S., Pitt, A., Arkin, R. C., & Kottege, N. (2023) · Autonomous Robots · doi:10.1007/s10514-023-10142-4 · Cited by 16
“Approaches range from pure behavior-based [5] to information-theoretic [6][7].”
BackgroundActive Visual SLAM with Exploration for Autonomous Underwater Navigation.
Kim, A. (2012) · Deep Blue (University of Michigan) · Cited by 16
Curiosity Based Exploration for Learning Terrain Models
Girdhar, Y., Whitney, D., & Dudek, G. (2015) · Cited by 14
Metadata
- Authors
- Bourgault, F., Makarenko, A. A., Williams, S. B., Grocholsky, B., & Durrant-Whyte, H. F.
- Affiliations
- The University of Sydney (AU)
- ORCID
- Williams, S.B.
- Venue
- IEEE/RSJ International Conference on Intelligent Robots and System
- Publisher
- IEEE
- Published
- 2003-06-25
- Volume
- 1
- Pages
- 540-545
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W2172103629
- Cited by
- 453
- References
- 12
- Citations by year
- 2026: 10 · 2025: 18 · 2024: 24 · 2023: 22 · 2022: 27 · 2021: 31 · 2020: 24 · 2019: 21 · 2018: 19 · 2017: 24 · 2016: 22 · 2015: 29 · 2014: 22 · 2013: 22 · 2012: 22
- FWCI
- 22.87
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robotic Path Planning Algorithms
- Keywords
- SLAM, occupancy grid mapping, mutual information, information gain, adaptive sensing, feature-based SLAM, laser scanner, mobile robots, indoor mapping, pose uncertainty
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.