Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Distributed Multi-agent Interaction Generation with Imagined Potential Games (2310.01614v1)

Published 2 Oct 2023 in cs.RO and cs.MA

Abstract: Interactive behavior modeling of multiple agents is an essential challenge in simulation, especially in scenarios when agents need to avoid collisions and cooperate at the same time. Humans can interact with others without explicit communication and navigate in scenarios when cooperation is required. In this work, we aim to model human interactions in this realistic setting, where each agent acts based on its observation and does not communicate with others. We propose a framework based on distributed potential games, where each agent imagines a cooperative game with other agents and solves the game using its estimation of their behavior. We utilize iLQR to solve the games and closed-loop simulate the interactions. We demonstrate the benefits of utilizing distributed imagined games in our framework through various simulation experiments. We show the high success rate, the increased navigation efficiency, and the ability to generate rich and realistic interactions with interpretable parameters. Illustrative examples are available at https://sites.google.com/berkeley.edu/distributed-interaction.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (40)
  1. S. Tang and V. Kumar, “Safe and complete trajectory generation for robot teams with higher-order dynamics,” in 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016, pp. 1894–1901.
  2. A. Desai and N. Michael, “Online planning for quadrotor teams in 3-d workspaces via reachability analysis on invariant geometric trees,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 8769–8775.
  3. J. van den Berg, S. J. Guy, M. Lin, and D. Manocha, “Reciprocal n-body collision avoidance,” in Robotics Research, C. Pradalier, R. Siegwart, and G. Hirzinger, Eds.   Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp. 3–19.
  4. D. Zhou, Z. Wang, S. Bandyopadhyay, and M. Schwager, “Fast, on-line collision avoidance for dynamic vehicles using buffered voronoi cells,” IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 1047–1054, 2017.
  5. B. Şenbaşlar, W. Hönig, and N. Ayanian, “Rlss: Real-time multi-robot trajectory replanning using linear spatial separations,” 2022.
  6. C. E. Luis, M. Vukosavljev, and A. P. Schoellig, “Online trajectory generation with distributed model predictive control for multi-robot motion planning,” IEEE Robotics and Automation Letters, vol. 5, no. 2, pp. 604–611, apr 2020.
  7. C. Wang, J. Bingham, and M. Tomizuka, “Trajectory splitting: A distributed formulation for collision avoiding trajectory optimization,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2021, pp. 8113–8120.
  8. A. Fonseca-Morales and O. Hernández-Lerma, “Potential Differential Games,” Dynamic Games and Applications, vol. 8, no. 2, pp. 254–279, June 2018. [Online]. Available: https://ideas.repec.org/a/spr/dyngam/v8y2018i2d10.1007_s13235-017-0218-6.html
  9. J. F. Fisac, E. Bronstein, E. Stefansson, D. Sadigh, S. S. Sastry, and A. D. Dragan, “Hierarchical game-theoretic planning for autonomous vehicles,” in 2019 International Conference on Robotics and Automation (ICRA), 2019, pp. 9590–9596.
  10. T. Kavuncu, A. Yaraneri, and N. Mehr, “Potential ilqr: A potential-minimizing controller for planning multi-agent interactive trajectories,” 2021.
  11. M. Wang, Z. Wang, J. Talbot, J. C. Gerdes, and M. Schwager, “Game-theoretic planning for self-driving cars in multivehicle competitive scenarios,” IEEE Transactions on Robotics, vol. 37, no. 4, pp. 1313–1325, 2021.
  12. J. Park, J. Kim, I. Jang, and H. J. Kim, “Efficient multi-agent trajectory planning with feasibility guarantee using relative bernstein polynomial,” in 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020, pp. 434–440.
  13. C. Wang, H.-C. Lin, S. Jin, X. Zhu, L. Sun, and M. Tomizuka, “Bpomp: A bilevel path optimization formulation for motion planning,” in 2022 American Control Conference (ACC).   IEEE, 2022, pp. 1891–1897.
  14. R. Spica, E. Cristofalo, Z. Wang, E. Montijano, and M. Schwager, “A real-time game theoretic planner for autonomous two-player drone racing,” IEEE Transactions on Robotics, vol. 36, no. 5, pp. 1389–1403, 2020.
  15. K. Miller and S. Mitra, “Multi-agent motion planning using differential games with lexicographic preferences,” in 2022 IEEE 61st Conference on Decision and Control (CDC), 2022, pp. 5751–5756.
  16. S. L. Cleac’h, M. Schwager, and Z. Manchester, “Algames: A fast augmented lagrangian solver for constrained dynamic games,” 2021.
  17. F. Laine, D. Fridovich-Keil, C.-Y. Chiu, and C. Tomlin, “The computation of approximate generalized feedback nash equilibria,” 2022.
  18. N. Mehr, M. Wang, M. Bhatt, and M. Schwager, “Maximum-entropy multi-agent dynamic games: Forward and inverse solutions,” IEEE Transactions on Robotics, vol. 39, no. 3, pp. 1801–1815, 2023.
  19. L. Wang, A. D. Ames, and M. Egerstedt, “Safety barrier certificates for collisions-free multirobot systems,” IEEE Transactions on Robotics, vol. 33, no. 3, pp. 661–674, 2017.
  20. Z. Jian, S. Zhang, L. Sun, W. Zhan, N. Zheng, and M. Tomizuka, “Long-term dynamic window approach for kinodynamic local planning in static and crowd environments,” IEEE Robotics and Automation Letters, vol. 8, no. 6, pp. 3294–3301, 2023.
  21. G. Sartoretti, J. Kerr, Y. Shi, G. Wagner, T. K. S. Kumar, S. Koenig, and H. Choset, “Primal: Pathfinding via reinforcement and imitation multi-agent learning,” IEEE Robotics and Automation Letters, vol. 4, no. 3, pp. 2378–2385, 2019.
  22. B. Rivière, W. Hönig, Y. Yue, and S.-J. Chung, “Glas: Global-to-local safe autonomy synthesis for multi-robot motion planning with end-to-end learning,” IEEE Robotics and Automation Letters, vol. 5, no. 3, pp. 4249–4256, 2020.
  23. Q. Li, F. Gama, A. Ribeiro, and A. Prorok, “Graph neural networks for decentralized multi-robot path planning,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, pp. 11 785–11 792.
  24. S. Batra, Z. Huang, A. Petrenko, T. Kumar, A. Molchanov, and G. S. Sukhatme, “Decentralized control of quadrotor swarms with end-to-end deep reinforcement learning,” 2021.
  25. J. Tordesillas and J. P. How, “Mader: Trajectory planner in multiagent and dynamic environments,” IEEE Transactions on Robotics, vol. 38, no. 1, pp. 463–476, 2022.
  26. Z. Williams, J. Chen, and N. Mehr, “Distributed potential ilqr: Scalable game-theoretic trajectory planning for multi-agent interactions,” in 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 01–07.
  27. R. A. Yeh, A. G. Schwing, J. Huang, and K. Murphy, “Diverse generation for multi-agent sports games,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  28. S. Suo, S. Regalado, S. Casas, and R. Urtasun, “Trafficsim: Learning to simulate realistic multi-agent behaviors,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2021, pp. 10 400–10 409.
  29. Z.-H. Yin, L. Sun, L. Sun, M. Tomizuka, and W. Zhan, “Diverse critical interaction generation for planning and planner evaluation,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021, pp. 7036–7043.
  30. W.-J. Chang, C. Tang, C. Li, Y. Hu, M. Tomizuka, and W. Zhan, “Editing driver character: Socially-controllable behavior generation for interactive traffic simulation,” IEEE Robotics and Automation Letters, vol. 8, no. 9, pp. 5432–5439, 2023.
  31. Q. Zhang, Y. Gao, Y. Zhang, Y. Guo, D. Ding, Y. Wang, P. Sun, and D. Zhao, “Trajgen: Generating realistic and diverse trajectories with reactive and feasible agent behaviors for autonomous driving,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 12, pp. 24 474–24 487, 2022.
  32. Z. Zhou, J. Wang, Y.-H. Li, and Y.-K. Huang, “Query-centric trajectory prediction,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
  33. L. Sun, C. Tang, Y. Niu, E. Sachdeva, C. Choi, T. Misu, M. Tomizuka, and W. Zhan, “Domain knowledge driven pseudo labels for interpretable goal-conditioned interactive trajectory prediction,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022, pp. 13 034–13 041.
  34. L. Sun, W. Zhan, D. Wang, and M. Tomizuka, “Interactive prediction for multiple, heterogeneous traffic participants with multi-agent hybrid dynamic bayesian network,” in 2019 IEEE Intelligent Transportation Systems Conference (ITSC), 2019, pp. 1025–1031.
  35. B. Piccoli and A. Tosin, “Pedestrian flows in bounded domains with obstacles,” Continuum Mechanics and Thermodynamics, vol. 21, no. 2, pp. 85–107, apr 2009. [Online]. Available: https://doi.org/10.1007%2Fs00161-009-0100-x
  36. W. van Toll, N. Jaklin, and R. Geraerts, “Towards believable crowds : A generic multi-level framework for agent navigation,” 2015. [Online]. Available: https://api.semanticscholar.org/CorpusID:14620077
  37. W. G. van Toll, A. F. Cook IV, and R. Geraerts, “Real-time density-based crowd simulation,” Computer Animation and Virtual Worlds, vol. 23, no. 1, pp. 59–69, 2012. [Online]. Available: https://onlinelibrary.wiley.com/doi/abs/10.1002/cav.1424
  38. S. Sarmady, F. Haron, and A. Z. H. Talib, “Modeling groups of pedestrians in least effort crowd movements using cellular automata,” in 2009 Third Asia International Conference on Modelling and Simulation, 2009, pp. 520–525.
  39. N. K. Mahato, A. Klar, and S. Tiwari, “Particle methods for multi-group pedestrian flow,” 2017.
  40. [Online]. Available: https://sites.google.com/berkeley.edu/distributed-interaction/
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Lingfeng Sun (25 papers)
  2. Pin-Yun Hung (2 papers)
  3. Changhao Wang (22 papers)
  4. Masayoshi Tomizuka (261 papers)
  5. Zhuo Xu (82 papers)
Citations (5)
View on Semantic Scholar