Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments

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. I. INTRODUCTIONAutonomous navigation of a team of robots in dynamic environments is important when deploying them in various applications such as coverage and inspection [1], search and rescue [2], formation flying [3] and multi-view videography [4]. In these scenarios, the robots navigate in a shared space that may also have moving obstacles. To achieve predictive collision avoidance and ensure safety, each robot needs to know the future motion predictions of other robots in the environment. These motion predictions can be obtained among robots by sharing their future planned trajectories with each other via communication [5]. However, such communication may not be available nor reliable in practice. Alternatively, some approaches [6] employ a constant velocity model to predict other robots' trajectories. Even though communication among robots is not required, the planned robot motions may not be safe, particularly in crowded dynamic environments [5].In this paper, we propose an interaction-and obstacleaware trajectory prediction model and combine it with * The authors contributed equally.

Model Predictive Control for Cooperative Transportation with Feasibility-Aware Policy

“…A similar NMPC application is studied and simulated in [37], which includes avoidance of collisions and of singular configurations for the manipulators. More recent studies like [38] propose data-driven MPC solutions, where each robot employs sensor data to predict the future behavior of the others, instead of relying on mutual communication. Two observations are now in order.…”

Time-series Imputation of Temporally-occluded Multiagent Trajectories

“…There exist a number of works from various fields of research that are related to our approach. Specifically, a number of works from robotics and computer vision [1,25,26,40], sports analytics [3,13,17,32,38], economics [28,35,36] and machine learning [6,11,33] focus on various combinations of missing data imputation and multiagent trajectory predictions. Given the broad scope of time series prediction as a research field [12], we focus particularly on models that predict human trajectories [25], as they are the most relevant for our problem regime.…”

Multi-Robot Leader Grouping Consistent Formation Control Method Research with Low Convergence Time Based on Nonholonomic Constraints

“…After more than 20 years of development, the multi-robot collaboration has shown a wide range of applications in the military, national defense, industry, life and other fields [4]. For example, it has shown great advantages in specific applications such as the formation patrol, environmental exploration, assembly-line production and warehousing and transportation [5][6][7]. Some specific application tasks include multi-robot cooperative map exploration, large object transportation, target capture and so on.…”