Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments
Authors:
- Hai ZhuHZHai Zhu
- Francisco Martinez ClaramuntFCFrancisco Martinez Claramunt
- Bruno BritoBBBruno Brito
- Javier Alonso-MoraJAJavier Alonso-Mora
Preprint
Abstract
This paper presents a data-driven decentralized trajectory optimization approach for multi-robot motion planning in dynamic environments. When navigating in a shared space, each robot needs accurate motion predictions of neighboring robots to achieve predictive collision avoidance. These motion predictions can be obtained among robots by sharing their future planned trajectories with each other via communication. However, such communication may not be available nor reliable in practice. In this paper, we introduce a novel trajectory prediction model based on recurrent neural networks (RNN) that can learn multi-robot motion behaviors from demonstrated trajectories generated using a centralized sequential planner. The learned model can run efficiently online for each robot and provide interaction-aware trajectory predictions of its neighbors based on observations of their history states. We then incorporate the trajectory prediction model into a decentralized model predictive control (MPC) framework for multi-robot collision avoidance. Simulation results show that our decentralized approach can achieve a comparable level of performance to a centralized planner while being communication-free and scalable to a large number of robots. We also validate our approach with a team of quadrotors in real-world experiments.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- GLAS: Global-to-Local Safe Autonomy Synthesis for Multi-Robot Motion Planning With End-to-End LearningIEEE Robotics and Automation Letters, 2020
- Multi-Agent Motion Planning for Dense and Dynamic Environments via Deep Reinforcement LearningIEEE Robotics and Automation Letters, 2020
- What the Constant Velocity Model Can Teach Us About Pedestrian Motion PredictionIEEE Robotics and Automation Letters, 2020
- Online Trajectory Generation With Distributed Model Predictive Control for Multi-Robot Motion PlanningIEEE Robotics and Automation Letters, 2020
- Chance-Constrained Collision Avoidance for MAVs in Dynamic EnvironmentsIEEE Robotics and Automation Letters, 2019
- Fast, On-line Collision Avoidance for Dynamic Vehicles Using Buffered Voronoi CellsIEEE Robotics and Automation Letters, 2017
- Understanding Human Avoidance Behavior: Interaction-Aware Decision Making Based on Game TheoryInternational Journal of Social Robotics, 2016
- Multi-Robot Search and Rescue: A Potential Field Based Approach2007
- Generalized force model of traffic dynamicsPhysical Review E, 1998
- Social force model for pedestrian dynamicsPhysical Review E, 1995