Bio-Inspired Collision Avoidance in Swarm Systems via Deep Reinforcement Learning
Open accessThe DOI matches its Crossref record; 58 of the 59 references it cites were found in a registry or an index.
Abstract
Autonomous vehicles have been highlighted as a major growth area for future transportation systems and the deployment of large numbers of these vehicles is expected when safety and legal challenges are overcome. To meet the necessary safety standards, effective collision avoidance technologies are required to ensure that the number of accidents are kept to a minimum. As large numbers of autonomous vehicles, operating together on roads, can be regarded as a swarm system, we propose a bio-inspired collision avoidance strategy using virtual pheromones; an approach that has evolved effectively in nature over many millions of years. Previous research using virtual pheromones showed the potential of pheromone-based systems to maneuver a swarm of robots. However, designing an individual controller to maximise the performance of the entire swarm is a major challenge. In this paper, we propose a novel deep reinforcement learning (DRL) based approach that is able to train a controller that introduces collision avoidance behaviour. To accelerate training, we propose a novel sampling strategy calledHighlight Experience Replayand integrate it with a Deep Deterministic Policy Gradient algorithm with noise added to the weights and biases of the artificial neural network to improve exploration. To evaluate the performance of the proposed DRL-based controller, we applied it to navigation and collision avoidance tasks in three different traffic scenarios. The experimental results showed that the proposed DRL-based controller outperformed the manually-tuned controller in terms of stability, effectiveness, robustness and ease of tuning process. Furthermore, the proposed Highlight Experience Replay method outperformed than the popular Prioritized Experience Replay sampling strategy by taking 27% of training time average over three stages.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
Human-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 3×
“The approach of using deep neural networks for reinforcement learning problem is referred to as DRL [40].”
BackgroundMethodInfluentialContinuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782 · cited 8×
“Due to its sample efficiency, this sampling strategy is used with DDPG in several continuous control domains including robotics [13], [47].”
MethodInfluentialProximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625 · cited 1×
“neural network to approximate the policy function and then the subsequent policy network is optimised [41], [42].”
BackgroundReinforcement Learning: An Introduction
Johnson, J. D., Li, J., & Chen, Z. (2000) · Neurocomputing · doi:10.1016/s0925-2312(00)00324-6 · Cited by 8,414
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 1×
“The third branch is actor-critic method [43].”
Trust region policy optimization
Schulman, J., Levine, S., Moritz, P., Jordan, M. I., & Abbeel, P. (2015) · arXiv · doi:10.48550/arxiv.1502.05477 · Cited by 4,578 · cited 1×
“neural network to approximate the policy function and then the subsequent policy network is optimised [41], [42].”
BackgroundSchaul, T., Quan, J., Antonoglou, I., & Silver, D. (2015) · arXiv · doi:10.48550/arxiv.1511.05952 · Cited by 3,120 · cited 3×
“strategy outperformed the Prioritized Experience Replay (PER) [32] sampling strategy in terms of training speed reducing to average 27% of training time with PER in three experimental stages.”
BackgroundMethodDorigo, M., Birattari, M., & Stutzle, T. (2006) · IEEE Computational Intelligence Magazine · doi:10.1109/ci-m.2006.248054 · Cited by 1,880
Reciprocal 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 17×
“As Turtlebot3, the robotic platform simulated in this work, is a non-holonomic wheeledmobile robot, NH-ORCA offers effective collision avoidance performance for our experimental setup.”
MethodInfluentialSwarm robotics: a review from the swarm engineering perspective
Brambilla, M., Ferrante, E., Birattari, M., & Dorigo, M. (2013) · Swarm Intelligence · doi:10.1007/s11721-012-0075-2 · Cited by 1,762 · cited 2×
“To alleviate the design challenges, automated design methods have been proposed to enable individual agents to learn optimal control rules without external intervention [30].”
BackgroundMethodAndrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., McGrew, B., Tobin, J., Abbeel, P., & Zaremba, W. (2017) · arXiv · doi:10.48550/arxiv.1707.01495 · Cited by 1,355 · cited 1×
“hindsight experience replay [45], attentive experience replay [46] and prioritised experience replay [32].”
BackgroundThe Superorganism: the beauty, elegance, and strangeness of insect societies
(2009) · Choice Reviews Online · doi:10.5860/choice.46-6805 · Cited by 1,205 · cited 1×
“One of the effective communication strategies that swarm systems utilise in nature is pheromone-based communication [17].”
BackgroundJi, J., Khajepour, A., Melek, W. W., & Huang, Y. (2017) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2016.2555853 · Cited by 1,039 · cited 1×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodComputational Methods for Fluid Dynamics
Ferziger, J. H., Perić, M., & Street, R. L. (2020) · Springer eBooks · doi:10.1007/978-3-319-99693-6 · Cited by 770
Pheromones and Animal Behavior: Chemical Signals and Signatures
Wyatt, T. D. (2014) · Cambridge University Press eBooks · doi:10.1017/cbo9781139030748 · Cited by 705
Collaborative Cloud and Edge Computing for Latency Minimization
Ren, J., Yu, G., He, Y., & Li, G. Y. (2019) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2019.2904244 · Cited by 685 · cited 1×
“number of fast moving autonomous vehicles, with minimal delays is feasible [35], [36].”
BackgroundDecentralized non-communicating multiagent collision avoidance with deep reinforcement learning
Chen, Y. F., Liu, M., Everett, M., & How, J. P. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989037 · Cited by 645
Dolcos, F., LaBar, K. S., & Cabeza, R. (2005) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0409848102 · Cited by 601
Noisy Networks for Exploration
Fortunato, M., Azar, M. G., Piot, B., Menick, J., Osband, I., Graves, A., Mnih, V., Munos, R., Hassabis, D., Pietquin, O., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.10295 · Cited by 543 · cited 2×
“training speed of HLER by integrating the Gaussian noise on parameters of a neural network (NN) to incentivise exploration for finding a better policy rapidly [33].”
BackgroundMethodNetworking and Communications in Autonomous Driving: A Survey
Wang, J., Liu, J., & Kato, N. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2018.2888904 · Cited by 536 · cited 1×
“are to receive widespread acceptance for use on roads then robust collision avoidance mechanisms in general operating environments are essential [2], [3].”
BackgroundLeveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards
Vecerik, M., Hester, T., Scholz, J., Wang, F., Pietquin, O., Piot, B., Heess, N., Rothörl, T., Lampe, T., & Riedmiller, M. (2017) · arXiv · doi:10.48550/arxiv.1707.08817 · Cited by 478 · cited 1×
“Due to its sample efficiency, this sampling strategy is used with DDPG in several continuous control domains including robotics [13], [47].”
MethodHu, J., Niu, H., Carrasco, J., Lennox, B., & Arvin, F. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3034800 · Cited by 438 · cited 3×
“Due to its sample efficiency, this sampling strategy is used with DDPG in several continuous control domains including robotics [13], [47].”
BackgroundMethodSelf-citationParameter Space Noise for Exploration
Plappert, M., Houthooft, R., Dhariwal, P., Sidor, S., Chen, R. Y., Chen, X., Asfour, T., Abbeel, P., & Andrychowicz, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.01905 · Cited by 346 · cited 1×
“space noise approach [51] requires manual fine-tuning of the noise parameters.”
BackgroundFan, T., Long, P., Liu, W., & Pan, J. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920916531 · Cited by 332
Reflections on the future of swarm robotics
Dorigo, M., Theraulaz, G., & Trianni, V. (2020) · Science Robotics · doi:10.1126/scirobotics.abe4385 · Cited by 282 · cited 1×
“challenge is the design of controllers for the individual agents within a swarm, that are able to maximise the performance of the entire swarm [28].”
BackgroundOptimal Reciprocal Collision Avoidance for Multiple Non-Holonomic Robots
Alonso-Mora, J., Breitenmoser, A., Rufli, M., Beardsley, P., & Siegwart, R. (2013) · Springer Tracts in Advanced Robotics · doi:10.1007/978-3-642-32723-0_15 · Cited by 280 · cited 16×
“As Turtlebot3, the robotic platform simulated in this work, is a non-holonomic wheeledmobile robot, NH-ORCA offers effective collision avoidance performance for our experimental setup.”
BackgroundInfluentialHu, J., Bhowmick, P., Arvin, F., Lanzon, A., & Lennox, B. (2020) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.2966412 · Cited by 221 · cited 1×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodSelf-citationSwarm Intelligence and cyber-physical systems: Concepts, challenges and future trends
Schranz, M., Di Caro, G. A., Schmickl, T., Elmenreich, W., Arvin, F., Şekercioğlu, A., & Sende, M. (2021) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2020.100762 · Cited by 187 · cited 1×
“a swarm is a system that consists of a large number of agents, controlled in a decentralised manner using local communication between individual agents or agents and the environment, that work towards a common goal [16].”
BackgroundSelf-citationCooperative Collision Avoidance for Nonholonomic Robots
Alonso-Mora, J., Beardsley, P., & Siegwart, R. (2018) · IEEE Transactions on Robotics · doi:10.1109/tro.2018.2793890 · Cited by 173 · cited 3×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodA model for the emergence of pillars, walls and royal chambers in termite nests
Bonabeau, E., Theraulaz, G., Deneubourg, J., Franks, N. R., Rafelsberger, O., Joly, J., & Blanco, S. (1998) · Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences · doi:10.1098/rstb.1998.0310 · Cited by 171
Kuru, K. (2021) · IEEE Access · doi:10.1109/access.2020.3049094 · Cited by 171 · cited 1×
“number of fast moving autonomous vehicles, with minimal delays is feasible [35], [36].”
BackgroundFu, Y., Li, C., Yu, F. R., Luan, T. H., & Zhang, Y. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3083927 · Cited by 169 · cited 1×
“are to receive widespread acceptance for use on roads then robust collision avoidance mechanisms in general operating environments are essential [2], [3].”
BackgroundEvolution of Collective Behaviors for a Real Swarm of Aquatic Surface Robots
Duarte, M., Costa, V., Gomes, J., Rodrigues, T., Silva, F., Oliveira, S. M., & Christensen, A. L. (2016) · PLOS ONE · doi:10.1371/journal.pone.0151834 · Cited by 134 · cited 1×
“agent communication strategies, and whilst showing promising results in realistic environments [31], they have not exploited the potential benefits offered through the use of pheromonebased techniques.”
BackgroundAutonomous Vehicles: State of the Art, Future Trends, and Challenges
Mallozzi, P., Pelliccione, P., Knauss, A., Berger, C., & Mohammadiha, N. (2019) · Springer eBooks · doi:10.1007/978-3-030-12157-0_16 · Cited by 132
Opposing effects of negative emotion on amygdalar and hippocampal memory for items and associations
Bisby, J. A., Horner, A. J., Hørlyck, L. D., & Burgess, N. (2016) · Social Cognitive and Affective Neuroscience · doi:10.1093/scan/nsw028 · Cited by 114 · cited 1×
“For example, in a study using brain imaging, it was found that images with negative emotions were retrieved more effectively than images that produced neutral emotions [49].”
BackgroundErk, S., Martin, S., & Walter, H. (2005) · NeuroImage · doi:10.1016/j.neuroimage.2005.02.045 · Cited by 109
A novel potential field method for obstacle avoidance and path planning of mobile robot
Tang, L., Dian, S., Gu, G., Zhou, K., Wang, S., & Feng, X. (2010) · IEEE International Conference on Computer Science and Information Technology · doi:10.1109/iccsit.2010.5565069 · Cited by 88 · cited 1×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodSun, P., Zhou, W., & Li, H. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6049 · Cited by 83 · cited 1×
“hindsight experience replay [45], attentive experience replay [46] and prioritised experience replay [32].”
BackgroundArtificial pheromone for path selection by a foraging swarm of robots
Campo, A., Gutiérrez, Á., Nouyan, S., Pinciroli, C., Longchamp, V., Garnier, S., & Dorigo, M. (2010) · Biological Cybernetics · doi:10.1007/s00422-010-0402-x · Cited by 81 · cited 1×
“A wide range of domains including optimisation [22], vehicle routing [23] and robotics [24]–[27] have recently adopted pheromone-based communication systems to address particular challenges.”
BackgroundAutomatic Off-Line Design of Robot Swarms: A Manifesto
Birattari, M., Ligot, A., Bozhinoski, D., Brambilla, M., Francesca, G., Garattoni, L., Garzón Ramos, D., Hasselmann, K., Kegeleirs, M., Kuckling, J., et al. (2019) · Frontiers in Robotics and AI · doi:10.3389/frobt.2019.00059 · Cited by 79 · cited 1×
“complexity of the task and environment increases [29].”
BackgroundBio-Inspired Embedded Vision System for Autonomous Micro-Robots: The LGMD Case
Hu, C., Arvin, F., Xiong, C., & Yue, S. (2016) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2016.2574624 · Cited by 74 · cited 1×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodSelf-citationA prototype IOT based wireless sensor network for traffic information monitoring
Huang, Y., Wang, L., Hou, Y., Zhang, W., & Zhang, Y. (2017) · International Journal of Pavement Research and Technology · doi:10.1016/j.ijprt.2017.07.005 · Cited by 68 · cited 1×
“The development of sensing technology and vehicle-toinfrastructure communication systems enabled to propose smart roads [37].”
BackgroundCOSΦ: Artificial pheromone system for robotic swarms research
Arvin, F., Krajník, T., Turgut, A. E., & Yue, S. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353405 · Cited by 57 · cited 2×
“The choice of eΦ for the volatile pheromone was inspired by [53], where highly volatile repellent pheromone was used to avoid collision with walls during navigation behaviours.”
BackgroundMethodSelf-citationForaging efficiency in the wood ant, Formica rufa: is time of the essence in trail following?
Denny, A. J., WRIGHT, J. M., & Grief, B. (2001) · Animal Behaviour · doi:10.1006/anbe.2001.1718 · Cited by 53
Kilogrid: a novel experimental environment for the Kilobot robot
Valentini, G., Antoun, A., Trabattoni, M., Wiandt, B., Tamura, Y., Hocquard, E., Trianni, V., & Dorigo, M. (2018) · Swarm Intelligence · doi:10.1007/s11721-018-0155-z · Cited by 52
RACE: Reinforced Cooperative Autonomous Vehicle Collision Avoidance
Yuan, Y., Tasik, R., Adhatarao, S. S., Yuan, Y., Liu, Z., & Fu, X. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.2974133 · Cited by 52 · cited 1×
“from large amounts of data that minimise collisions involving autonomous vehicles [13], [14].”
BackgroundCzaczkes, T. J., & Heınze, J. (2015) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2015.0679 · Cited by 48
Bio-inspired artificial pheromone system for swarm robotics applications
Na, S., Qiu, Y., Turgut, A. E., Ulrich, J., Krajník, T., Yue, S., Lennox, B., & Arvin, F. (2021) · Adaptive Behavior · doi:10.1177/1059712320918936 · Cited by 47 · cited 1×
“A wide range of domains including optimisation [22], vehicle routing [23] and robotics [24]–[27] have recently adopted pheromone-based communication systems to address particular challenges.”
BackgroundSelf-citationSoon, K. L., Lim, J. M.-Y., & Parthiban, R. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.105486 · Cited by 45 · cited 1×
“A wide range of domains including optimisation [22], vehicle routing [23] and robotics [24]–[27] have recently adopted pheromone-based communication systems to address particular challenges.”
BackgroundAccelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player
Niu, H., Ji, Z., Arvin, F., Lennox, B., Yin, H., & Carrasco, J. (2021) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/ieeeconf49454.2021.9382693 · Cited by 43
Self-citationUrban Swarms: A new approach for autonomous waste management
Alfeo, A. L., Ferrer, E. C., Carrillo, Y. L., Grignard, A., Pastor, L. A., Sleeper, D. T., Cimino, M. G. C. A., Lepri, B., Vaglini, G., Larson, K., et al. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794020 · Cited by 37 · cited 2×
“For example, in [21], the effectiveness of pheromonebased communications was demonstrated in an urban waste”
BackgroundSalman, M., Garzón Ramos, D., Hasselmann, K., & Birattari, M. (2020) · Frontiers in Robotics and AI · doi:10.3389/frobt.2020.591402 · Cited by 27
Repellent pheromones for effective swarm robot search in unknown environments
Fossum, F., Montanier, J.-M., & Haddow, P. C. (2014) · IEEE Swarm Intelligence Symposium · doi:10.1109/sis.2014.7011802 · Cited by 23
A Model-free Deep Reinforcement Learning Approach for Robotic Manipulators Path Planning
Liu, W., Niu, H., Mahyuddin, M. N., Herrmann, G., & Carrasco, J. (2021) · International Conference on Control, Automation and Systems (ICCAS) · doi:10.23919/iccas52745.2021.9649802 · Cited by 22
Self-citationAdaptive AEB Control Strategy for Collision Avoidance Including Rear Vehicles
Shin, S.-G., Ahn, D.-R., Baek, Y.-S., & Lee, H.-K. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8916988 · Cited by 21 · cited 1×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodShort-Term Multi-Vehicle Trajectory Planning for Collision Avoidance
Nakamura, A., Liu, Y.-C., & Kim, B. (2020) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2020.3004752 · Cited by 19 · cited 1×
“which have been based on numerous techniques including control theory [4], potential fields [5], trajectory planning [6], adaptive control [7], [8], velocity-based approaches [9]–[11] and biologically-inspired method [12].”
MethodExtended Artificial Pheromone System for Swarm Robotic Applications
Na, S., Raoufi, M., Turgut, A. E., Krajník, T., & Arvin, F. (2019) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal_a_00228 · Cited by 11 · cited 1×
“The design of the pheromone-based collision avoidance technique was inspired from [53], [54].”
MethodSelf-citationUniversal Artificial Pheromone Framework with Deep Reinforcement Learning for Robotic Systems
Na, S., Niu, H., Lennox, B., & Arvin, F. (2021) · International Conference on Control and Robotics Engineering (ICCRE) · doi:10.1109/iccre51898.2021.9435666 · Cited by 6 · cited 1×
“Compared to our previous work [34] that first validated the PhERS framework, the”
ResultSelf-citation
Research works printed but not linked: 1
- 10.1109/mci.2006.329691 · doi:10.1109/mci.2006.329691 · Paper page
Cited by
Reinforcement learning algorithms: A brief survey
Shakya, A. K., Pillai, G., & Chakrabarty, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120495 · Cited by 656
Multi-Agent Deep Reinforcement Learning for Multi-Robot Applications: A Survey
Orr, J., & Dutta, A. (2023) · Sensors · doi:10.3390/s23073625 · Cited by 206
“The foundation of the algorithm is also based on DQN. Na et al. [49] have used MADRL for collision avoidance among autonomous vehicles via modeling virtual pheromones inspired by nature.”
MethodDistributed Motion Planning for Safe Autonomous Vehicle Overtaking via Artificial Potential Field
Xie, S., Hu, J., Bhowmick, P., Ding, Z., & Arvin, F. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3189741 · Cited by 179
“Deep deterministic strategy gradient method and deep Q-learning network become the mainstream algorithm frameworks [40], [41].”
MethodSelf-citationWu, K., Hu, J., Ding, Z., & Arvin, F. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3239748 · Cited by 90
“…have been widely used in practical robotic applications, such as collaborative manipulators [1], object transportation [2], search and rescue [3], [4], [5], ecosystem hacking using micro-robot swarms [6], exploration in unknown environments [7], autonomous vehicle platooning [8], [9], [10], etc.”
MethodSelf-citationHuman-in-the-Loop Robot Learning for Smart Manufacturing: A Human-Centric Perspective
Chen, H., Li, S., Fan, J., Duan, A., Yang, C., Navarro-Alarcon, D., & Zheng, P. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3528051 · Cited by 67
“Na et al. [166] designed a collision avoidance behavior for swarm systems based on a virtual pheromone, making robot navigation and collision avoidance tasks in different scenarios.”
Metadata
- Authors
- Na, S., Niu, H., Lennox, B., & Arvin, F.
- Affiliations
- University of Manchester (GB)
- Venue
- IEEE Transactions on Vehicular Technology
- Published
- 2022-03
- Volume
- 71
- Issue
- 3
- Pages
- 2511-2526
- ISSN
- 0018-9545 (ISSN-L)
- 1939-9359
- OpenAlex
- W4210530701
- Cited by
- 64
- References
- 59
- Citations by year
- 2026: 4 · 2025: 19 · 2024: 12 · 2023: 25 · 2022: 4
- FWCI
- 4.94
- Type
- journal article
- Language
- en
- Open access
- Licence
- Locations
- IEEE Transactions on Vehicular Technology (publishedVersion)
- Research Explorer (The University of Manchester) (acceptedVersion, other-oa)
- Durham Research Online (Durham University) (submittedVersion)
- Durham Research Online (Durham University) (submittedVersion, cc-by)
- Funders
- EU H2020-FET-OPEN RoboRoyale Project (964492)
- Engineering and Physical Sciences Research Council (EP/R026084/1, EP/P01366X/1)
- University of Manchester
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Engineering › Control and Systems Engineering › Traffic control and management
- Keywords
- collision avoidance, autonomous vehicles, swarm systems, virtual pheromones, bio-inspired control, deep reinforcement learning, deep deterministic policy gradient, exploration noise, traffic scenarios, vehicle navigation
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.