Multi-Agent Path Integral Control for Interaction-Aware Motion Planning in Urban Canals

TL;DR

This paper presents a decentralized, interaction-aware motion planning method for autonomous surface vessels in urban canals, leveraging a sampling-based control approach to ensure collision avoidance, rule compliance, and robustness in multi-agent scenarios.

Contribution

It introduces a novel decentralized, communication-free motion planner based on MPPI for urban canal vessels, incorporating interaction modeling and efficiency improvements.

Findings

Outperforms existing trajectory optimization methods in simulations.

Demonstrates robustness in diverse multi-agent scenarios.

Ensures rule compliance and collision avoidance in complex environments.

Abstract

Autonomous vehicles that operate in urban environments shall comply with existing rules and reason about the interactions with other decision-making agents. In this paper, we introduce a decentralized and communication-free interaction-aware motion planner and apply it to Autonomous Surface Vessels (ASVs) in urban canals. We build upon a sampling-based method, namely Model Predictive Path Integral control (MPPI), and employ it to, in each time instance, compute both a collision-free trajectory for the vehicle and a prediction of other agents' trajectories, thus modeling interactions. To improve the method's efficiency in multi-agent scenarios, we introduce a two-stage sample evaluation strategy and define an appropriate cost function to achieve rule compliance. We evaluate this decentralized approach in simulations with multiple vessels in real scenarios extracted from Amsterdam's canals, showing superior performance than a state-of-the-art trajectory optimization framework and robustness when encountering different types of agents.