Hybrid Dynamic Moving Obstacle Avoidance Using a Stochastic Reachable Set-Based Potential Field
The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.
Abstract
One of the primary challenges for autonomous robotics in uncertain and dynamic environments is planning and executing a collision-free path. Hybrid dynamic obstacles present an even greater challenge as the obstacles can change dynamics without warning and potentially invalidate paths. Artificial potential field (APF)-based techniques have shown great promise in successful path planning in highly dynamic environments due to their low cost at runtime. We utilize the APF framework for runtime planning but leverage a formal validation method, Stochastic Reachable (SR) sets, to generate accurate potential fields for moving obstacles. A small number of SR sets are computed a priori, then used to generate a potential field that represents the obstacle's stochastic motion for online path planning. Our method is novel and scales well with the number of obstacles, maintaining a relatively high probability of reaching the goal without collision, as compared to other traditional Gaussian APF methods. Here, we demonstrate our method with up to 900 hybrid dynamic obstacles and show that it outperforms the traditional Gaussian APF method by up to 60% in the holonomic case and up to 20% in the unicycle case.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
(1995) · Cited by 10,558
Real-Time Obstacle Avoidance for Manipulators and Mobile Robots
Khatib, O. (1986) · The International Journal of Robotics Research · doi:10.1177/027836498600500106 · Cited by 7,894 · cited 1×
“These methods generate an artificial potential in the robot’s workspace, which repels the robot from obstacles and attracts the robot to the goal [34].”
MethodThe interacting multiple model algorithm for systems with Markovian switching coefficients
Blom, H. A. P., & Bar-Shalom, Y. (1988) · IEEE Transactions on Automatic Control · doi:10.1109/9.1299 · Cited by 2,460 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundMotion Planning in Dynamic Environments Using Velocity Obstacles
Fiorini, P., & Shiller, Z. (1998) · The International Journal of Robotics Research · doi:10.1177/027836499801700706 · Cited by 2,008 · cited 2×
“Velocity obstacles (VO) [24] are widely used for path planning with moving obstacles.”
BackgroundMethodReciprocal n-Body Collision Avoidance
van den Berg, J., Guy, S. J., Lin, M., & Manocha, D. (2011) · Springer Tracts in Advanced Robotics · doi:10.1007/978-3-642-19457-3_1 · Cited by 1,858 · cited 5×
“The authors would like to thank N. Rackley and S. Cutlip for the modification of ORCA and for the calculation of the hybrid SR set, respectively.”
BackgroundMethodInfluentialInteracting multiple model methods in target tracking: a survey
Mazor, E., Averbuch, A., Bar-Shalom, Y., & Dayan, J. (1998) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/7.640267 · Cited by 1,179 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundA time-dependent Hamilton-Jacobi formulation of reachable sets for continuous dynamic games
Mitchell, I. M., Bayen, A. M., & Tomlin, C. J. (2005) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2005.851439 · Cited by 1,152 · cited 1×
“, obstacle) inputs [48], [45], [29].”
Conflict resolution for air traffic management: a study in multiagent hybrid systems
Tomlin, C., Pappas, G. J., & Sastry, S. (1998) · IEEE Transactions on Automatic Control · doi:10.1109/9.664154 · Cited by 1,042 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundPath Planning for Autonomous Vehicles in Unknown Semi-structured Environments
Dolgov, D., Thrun, S., Montemerlo, M., & Diebel, J. (2010) · The International Journal of Robotics Research · doi:10.1177/0278364909359210 · Cited by 976 · cited 3×
“[26], and navigation in narrow passages is required [19].”
BackgroundMethodNew potential functions for mobile robot path planning
Ge, S. S., & Cui, Y. (2000) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.880813 · Cited by 868 · cited 4×
“[26], and navigation in narrow passages is required [19].”
BackgroundMethodInfluentialBohlin, R., & Kavraki, L. E. (2000) · Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065) · doi:10.1109/robot.2000.844107 · Cited by 856 · cited 1×
“Common approaches to solve the motion planning problem for dynamic obstacles include artificial potential field (APF) methods [11], [26], [35], [38], tree-based planners [40], [49], Probabilistic Roadmap Methods (PRMs) [32], [43], [57], [67], and several variants which use heuristics [3], [10].”
BackgroundReal-Time Motion Planning for Agile Autonomous Vehicles
Frazzoli, E., Dahleh, M. A., & Feron, E. (2002) · Journal of Guidance, Control, and Dynamics · doi:10.2514/2.4856 · Cited by 830
Dynamic Motion Planning for Mobile Robots Using Potential Field Method
Ge, S. S., & Cui, Y. J. (2002) · Autonomous Robots · doi:10.1023/a:1020564024509 · Cited by 803 · cited 1×
“We also evaluated the improved performance of incorporating SR sets with APF methods, as opposed to ad hoc methods [27], [38], [66] for computing repulsion fields.”
MethodProbabilistic reachability and safety for controlled discrete time stochastic hybrid systems
Abate, A., Prandini, M., Lygeros, J., & Sastry, S. (2008) · Automatica · doi:10.1016/j.automatica.2008.03.027 · Cited by 539 · cited 2×
“of the state space with a certain probability [2], [56], [61].”
BackgroundMethodTemporal logic motion planning for dynamic robots
Fainekos, G., Girard, A., Kress‐Gazit, H., & Pappas, G. J. (2008) · Automatica · doi:10.1016/j.automatica.2008.08.008 · Cited by 514 · cited 1×
“” For example, the authors in [22] consider the temporal logic for motion planning with dynamic robots and static, known obstacles, and use formal methods to construct paths that are provably guaranteed to meet the desired specifications.”
BackgroundSampling-Based Path Planning on Configuration-Space Costmaps
Jaillet, L., Cortés, J., & Siméon, T. (2010) · IEEE Transactions on Robotics · doi:10.1109/tro.2010.2049527 · Cited by 367 · cited 1×
“For example, Jaillet et al.[31] used a user-defined cost-map to influence node placement in a Rapidly exploring Random Tree (RRT) algorithm.”
Computational techniques for the verification of hybrid systems
Tomlin, C. J., Mitchell, I., Bayen, A. M., & Oishi, M. (2003) · Proceedings of the IEEE · doi:10.1109/jproc.2003.814621 · Cited by 353
Self-citationEvolutionary artificial potential fields and their application in real time robot path planning
Vadakkepat, P., Tan, K. C., & Ming-Liang, W. (2002) · Proceedings of the 2000 Congress on Evolutionary Computation. CEC00 (Cat. No.00TH8512) · doi:10.1109/cec.2000.870304 · Cited by 346 · cited 2×
“Other recent work has focused on modification of the computation of the potential field through fuzzy [59] and evolutionary [65] APFs.”
MethodDirecting Crowd Simulations Using Navigation Fields
Patil, S., van den Berg, J., Curtis, S., Lin, M. C., & Manocha, D. (2010) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2010.33 · Cited by 242
Anytime path planning and replanning in dynamic environments
van den Berg, J., Ferguson, D., & Kuffner, J. (2006) · Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006. · doi:10.1109/robot.2006.1642056 · Cited by 241 · cited 1×
“Common approaches to solve the motion planning problem for dynamic obstacles include artificial potential field (APF) methods [11], [26], [35], [38], tree-based planners [40], [49], Probabilistic Roadmap Methods (PRMs) [32], [43], [57], [67], and several variants which use heuristics [3], [10].”
BackgroundDecentralized Cooperative Policy for Conflict Resolution in Multivehicle Systems
Pallottino, L., Scordio, V. G., Bicchi, A., & Frazzoli, E. (2007) · IEEE Transactions on Robotics · doi:10.1109/tro.2007.909810 · Cited by 234 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundApproximate Model Checking of Stochastic Hybrid Systems
Abate, A., Katoen, J.-P., Lygeros, J., & Prandini, M. (2010) · European Journal of Control · doi:10.3166/ejc.16.624-641 · Cited by 181 · cited 2×
“A robot whose motion is probabilistic, and modeled as a Markov decision process (MDP), is considered in [37], and the optimal strategy and maximal probability of successful navigation in a static environment are computed.”
MethodSoudjani, S., & Abate, A. (2013) · SIAM Journal on Applied Dynamical Systems · doi:10.1137/120871456 · Cited by 171 · cited 1×
“The computational techniques used to solve these reachability problems rely on solving a dynamic program by modeling the system as a finite state MDP [1], [21].”
MethodA PRM-based motion planner for dynamically changing environments
Jaillet, L., & Simeon, T. (2005) · 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566) · doi:10.1109/iros.2004.1389625 · Cited by 164 · cited 2×
“SR-Query was more successful in identifying collision-free paths in environments with 50 moving obstacles than a roadmap-based approach that simply pruned invalid edges during dynamic path queries [32], but was susceptible to fast unseen moving obstacles, due to limited reactivity and required navigation on the roadma…”
BackgroundMethodHuman-Centered Robot Navigation—Towards a Harmoniously Human–Robot Coexisting Environment
Lam, C.-P., Chou, C.-T., Chiang, K.-H., & Fu, L.-C. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2010.2076851 · Cited by 164 · cited 3×
“We also evaluated the improved performance of incorporating SR sets with APF methods, as opposed to ad hoc methods [27], [38], [66] for computing repulsion fields.”
BackgroundMethodTemporal Logic Motion Planning and Control With Probabilistic Satisfaction Guarantees
Lahijanian, M., Andersson, S. B., & Belta, C. A. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2172150 · Cited by 163 · cited 1×
“A robot whose motion is probabilistic, and modeled as a Markov decision process (MDP), is considered in [37], and the optimal strategy and maximal probability of successful navigation in a static environment are computed.”
BackgroundApplications of hybrid reachability analysis to robotic aerial vehicles
Gillula, J., Hoffmann, G. M., Huang, H., Vitus, M. P., & Tomlin, C. J. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364910387173 · Cited by 159 · cited 1×
“, obstacle) inputs [48], [45], [29].”
Chiang, H.-T. L., Malone, N., Lesser, K., Oishi, M., & Tapia, L. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139511 · Cited by 149 · cited 3×
“Another branch of work on APFs utilizes the repulsive and attractive concepts of APFs, but also integrates another path planning method [31], [55], [14].”
BackgroundMethodSelf-citationIntent-Based Probabilistic Conflict Detection for the Next Generation Air Transportation System
Hwang, I., & Seah, C. E. (2008) · Proceedings of the IEEE · doi:10.1109/jproc.2008.2006138 · Cited by 131 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundMobile robot navigation in 2-D dynamic environments using an electrostatic potential field
Valavanis, K. P., Hebert, T., Kolluru, R., & Tsourveloudis, N. C. (2000) · IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans · doi:10.1109/3468.833100 · Cited by 114 · cited 1×
“We also evaluated the improved performance of incorporating SR sets with APF methods, as opposed to ad hoc methods [27], [38], [66] for computing repulsion fields.”
MethodOtte, M., & Frazzoli, E. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-16595-0_27 · Cited by 108 · cited 6×
“Alternately, Otte and Frazzoli [53] extend RRTs to dynamic obstacles by repairing subtrees invalidated by moving obsta-”
BackgroundInfluentialLocal Multiresolution Path Planning
Behnke, S. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-25940-4_29 · Cited by 102 · cited 1×
“Traditionally, multi-resolution planning uses a coarse grid to restrict the planning space on a global scale and then uses finer resolution grids in the restricted area [9], [5].”
BackgroundRobust Online Motion Planning with Regions of Finite Time Invariance
Majumdar, A., & Tedrake, R. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-36279-8_33 · Cited by 97 · cited 2×
“Beyond the scope of this work, this approximation facilitates the integration of new methods that might maintain a SR set database which could be used to match obstacle motion to sets (as was done with funnel libraries [42]) or predictions of dynamic obstacle motions [23].”
BackgroundMethodAnytime Safe Interval Path Planning for dynamic environments
Narayanan, V., Phillips, M., & Likhachev, M. A. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386191 · Cited by 95 · cited 1×
“Common approaches to solve the motion planning problem for dynamic obstacles include artificial potential field (APF) methods [11], [26], [35], [38], tree-based planners [40], [49], Probabilistic Roadmap Methods (PRMs) [32], [43], [57], [67], and several variants which use heuristics [3], [10].”
BackgroundIterative temporal motion planning for hybrid systems in partially unknown environments
Maly, M. R., Lahijanian, M., Kavraki, L. E., Kress‐Gazit, H., & Vardi, M. Y. (2013) · International Conference on Hybrid Systems: computation and control · doi:10.1145/2461328.2461380 · Cited by 90 · cited 1×
“, [44] and [4].”
Reachability calculations for automated aerial refueling
Ding, J., Sprinkle, J. M., Sastry, S., & Tomlin, C. J. (2008) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2008.4738998 · Cited by 71 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundReachability-based synthesis of feedback policies for motion planning under bounded disturbances
Ding, J., Li, E., Huang, H., & Tomlin, C. J. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980268 · Cited by 67 · cited 1×
“approach is taken in [17], but reachable sets are computed iteratively so that the robot can modify its actions.”
BackgroundPath planning in practice; lazy evaluation on a multi-resolution grid
Bohlin, R. (2002) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2001.973335 · Cited by 56 · cited 1×
“Traditionally, multi-resolution planning uses a coarse grid to restrict the planning space on a global scale and then uses finer resolution grids in the restricted area [9], [5].”
BackgroundFerguson, S., Luders, B. D., Grande, R. C., & How, J. P. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-16595-0_10 · Cited by 55
A stochastic games framework for verification and control of discrete time stochastic hybrid systems
Ding, J., Kamgarpour, M., Summers, S., Abate, A., Lygeros, J., & Tomlin, C. J. (2013) · Automatica · doi:10.1016/j.automatica.2013.05.025 · Cited by 54 · cited 1×
“In [16], a two-player stochastic dynamical game is applied to a target tracking application in which the target acts in opposition to the tracker.”
MethodPath planning with uncertainty: Voronoi Uncertainty Fields
Ok, K., Ansari, S., Gallagher, B., Sica, W., Dellaert, F., & Stilman, M. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631230 · Cited by 51 · cited 1×
“Voronoi decomposition was used in [52] to generate a global plan and then uses APF for local planning along the”
MethodTemporal logic motion planning in unknown environments
Ayala, A. I. M., Andersson, S. B., & Belta, C. A. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6697120 · Cited by 45
Using non-linear velocity obstacles to plan motions in a dynamic environment
Large, F., Sckhavat, S., Shiller, Z., & Laugier, C. (2004) · International Conference on Control, Automation, Robotics and Vision (ICARCV) · doi:10.1109/icarcv.2002.1238513 · Cited by 43 · cited 1×
“Additional VO formulation incorporated arcing motion obstacles, allowing an algorithm to handle both linear and arcing motion obstacles [39].”
BackgroundStochastic reachability based motion planning for multiple moving obstacle avoidance
Malone, N., Lesser, K., Oishi, M., & Tapia, L. (2014) · International Conference on Hybrid Systems: computation and control · doi:10.1145/2562059.2562127 · Cited by 36 · cited 3×
“Further discussion and the derivation of (16) is given in [43].”
BackgroundMethodSelf-citationReactive Path Planning for Micro Air Vehicles Using Bearing-only Measurements
Sharma, R., Saunders, J. B., & Beard, R. W. (2011) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-011-9617-x · Cited by 34 · cited 1×
“The work in [58] uses a reactive controller which is tuned to avoid certain classes of pop-up obstacles, such as cylinders, combined with way-point following to guide a holonomic micro-UAV.”
MethodTakei, R., Huang, H., Ding, J., & Tomlin, C. J. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225074 · Cited by 32 · cited 1×
“In [62], reachable sets are calculated to assure a robot safely reaches a target while avoiding a single obstacle, whose motion is chosen to maximize collision, and the robot cannot modify its movements based on subsequent observations.”
BackgroundAggressive Moving Obstacle Avoidance Using a Stochastic Reachable Set Based Potential Field
Chiang, H.-T. L., Malone, N., Lesser, K., Oishi, M., & Tapia, L. (2015) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-16595-0_5 · Cited by 29 · cited 3×
“Using single mode dynamics (arc/line) as in [13], the memory requirement is 117 KB.”
MethodSelf-citationHierarchical Planning with 3D Local Multiresolution Obstacle Avoidance for Micro Aerial Vehicles
Nieuwenhuisen, M., & Behnke, S. (2014) · International Symposium on Robotics · Cited by 29
Chiang, H.-T. L., HomChaudhuri, B., Vinod, A. P., Oishi, M., & Tapia, L. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989434 · Cited by 28 · cited 1×
“[15] and [12] predict obstacle motion by Monte Carlo simulations and forward reachability analysis, respectively.”
Self-citationLayered Mission and Path Planning for MAV Navigation with Partial Environment Knowledge
Nieuwenhuisen, M., & Behnke, S. (2015) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-08338-4_23 · Cited by 27 · cited 1×
“variant was used in [50] and [51] for reactive planning, but they also construct a hierarchy of successively more forward-looking path planners (eventually ending with a mission planner).”
MethodA framework for planning motion in environments with moving obstacles
Rodríguez, S., Lien, J., & Amato, N. M. (2007) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2007.4399540 · Cited by 26 · cited 1×
“Common approaches to solve the motion planning problem for dynamic obstacles include artificial potential field (APF) methods [11], [26], [35], [38], tree-based planners [40], [49], Probabilistic Roadmap Methods (PRMs) [32], [43], [57], [67], and several variants which use heuristics [3], [10].”
BackgroundKluge, B., & Prassler, E. A. (2007) · Springer eBooks · doi:10.1007/978-3-540-73422-2_6 · Cited by 25
Stochastic Ensemble Simulation motion planning in stochastic dynamic environments
Chiang, H.-T. L., Rackley, N., & Tapia, L. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353916 · Cited by 21 · cited 1×
“[15] and [12] predict obstacle motion by Monte Carlo simulations and forward reachability analysis, respectively.”
Self-citationGrafting: A Path Replanning Technique for Rapidly-Exploring Random Trees in Dynamic Environments
Lee, H.-C., Touahmi, Y., & Lee, B. H. (2012) · Advanced Robotics · doi:10.1080/01691864.2012.703301 · Cited by 21 · cited 1×
“Common approaches to solve the motion planning problem for dynamic obstacles include artificial potential field (APF) methods [11], [26], [35], [38], tree-based planners [40], [49], Probabilistic Roadmap Methods (PRMs) [32], [43], [57], [67], and several variants which use heuristics [3], [10].”
BackgroundFormal design of a provably safe robotic roundabout system
Duperret, J. M., Hafner, M. R., & Del Vecchio, D. (2010) · 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2010.5649789 · Cited by 18 · cited 1×
“in models of multivehicle conflict resolution [7], [20], [54], [63], [64], aircraft target tracking [8], [30], [47], and in other applications [18] which require mathematically tractable yet realistic”
BackgroundKluge, B. (2004) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2003.1250657 · Cited by 15 · cited 1×
“Frameworks have also been proposed for planning with stochastically moving obstacles by iterating through all possible robot velocities in order to approximate the true VO and find the optimal velocity [36].”
BackgroundAn optimizing sampling-based motion planner with guaranteed robustness to bounded uncertainty
Luders, B. D., & How, J. P. (2014) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2014.6859383 · Cited by 14 · cited 1×
“[41] applies robust control in the expansion step of the RRT algorithm.”
Method
Metadata
- Authors
- Malone, N., Chiang, H.-T., Lesser, K., Oishi, M., & Tapia, L.
- Venue
- IEEE Transactions on Robotics
- Published
- 2017-10
- Volume
- 33
- Issue
- 5
- Pages
- 1124-1138
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2624934338
- Cited by
- 173
- References
- 57
- FWCI
- 5.50
- Type
- journal article
- Language
- en
- Open access
- closed
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.