Topology-Guided ORCA: Smooth Multi-Agent Motion Planning in Constrained Environments (2407.16771v2)
Abstract: We present Topology-Guided ORCA as an alternative simulator to replace ORCA for planning smooth multi-agent motions in environments with static obstacles. Despite the impressive performance in simulating multi-agent crowd motion in free space, ORCA encounters a significant challenge in navigating the agents with the presence of static obstacles. ORCA ignores static obstacles until an agent gets too close to an obstacle, and the agent will get stuck if the obstacle intercepts an agent's path toward the goal. To address this challenge, Topology-Guided ORCA constructs a graph to represent the topology of the traversable region of the environment. We use a path planner to plan a path of waypoints that connects each agent's start and goal positions. The waypoints are used as a sequence of goals to guide ORCA. The experiments of crowd simulation in constrained environments show that our method outperforms ORCA in terms of generating smooth and natural motions of multiple agents in constrained environments, which indicates great potential of Topology-Guided ORCA for serving as an effective simulator for training constrained social navigation policies.
- V-rvo: Decentralized multi-agent collision avoidance using voronoi diagrams and reciprocal velocity obstacles. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 8097–8104. IEEE, 2021. doi: 10.1109/IROS51168.2021.9636618. URL https://ieeexplore.ieee.org/document/9636618.
- Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. In 2019 international conference on robotics and automation (ICRA), pages 6015–6022. IEEE, 2019. doi: 10.1109/ICRA.2019.8794134. URL https://ieeexplore.ieee.org/document/8794134.
- Socially aware motion planning with deep reinforcement learning. In 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 1343–1350. IEEE, 2017. doi: 10.1109/IROS.2017.8202312. URL https://ieeexplore.ieee.org/document/8202312.
- Motion planning in dynamic environments using velocity obstacles. The international journal of robotics research, 17(7):760–772, 1998. doi: 10.1177/027836499801700706. URL https://journals.sagepub.com/doi/10.1177/027836499801700706.
- Intention aware robot crowd navigation with attention-based interaction graph. In 2023 IEEE International Conference on Robotics and Automation (ICRA), pages 12015–12021. IEEE, 2023. doi: 10.1109/ICRA48891.2023.10160660. URL https://ieeexplore.ieee.org/document/10160660.
- Robot navigation in constrained pedestrian environments using reinforcement learning. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pages 1140–1146. IEEE, 2021. doi: 10.1109/ICRA48506.2021.9560893. URL https://ieeexplore.ieee.org/document/9560893.
- Reciprocal velocity obstacles for real-time multi-agent navigation. In 2008 IEEE international conference on robotics and automation, pages 1928–1935. Ieee, 2008. doi: 10.1109/ROBOT.2008.4543489. URL https://ieeexplore.ieee.org/document/4543489.
- Reciprocal n-body collision avoidance. In Robotics Research: The 14th International Symposium ISRR, pages 3–19. Springer, 2011. doi: 10.1007/978-3-642-19457-3˙1. URL https://link.springer.com/chapter/10.1007/978-3-642-19457-3_1.
- A fast parallel algorithm for thinning digital patterns. Commun. ACM, 27:236–239, 1984. doi: 10.1145/357994.358023. URL https://dl.acm.org/doi/10.1145/357994.358023.
- Fatemeh Cheraghi Pouria (4 papers)
- Zhe Huang (57 papers)
- Ananya Yammanuru (4 papers)
- Shuijing Liu (18 papers)
- Katherine Driggs-Campbell (77 papers)