PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner

TL;DR

PRIMER is a learning-based multiagent trajectory planner that significantly speeds up planning by mimicking an optimization-based method, enabling real-time collision avoidance in uncertain environments.

Contribution

The paper introduces PRIMER, a neural network-based planner trained via imitation learning to replicate PARM*'s performance with much lower computational cost.

Findings

PRIMER achieves up to 5500x faster computation than optimization-based methods.

It maintains high-quality trajectory planning in uncertain environments.

The approach enables real-time multiagent navigation with perception-awareness.

Abstract

In decentralized multiagent trajectory planners, agents need to communicate and exchange their positions to generate collision-free trajectories. However, due to localization errors/uncertainties, trajectory deconfliction can fail even if trajectories are perfectly shared between agents. To address this issue, we first present PARM and PARM*, perception-aware, decentralized, asynchronous multiagent trajectory planners that enable a team of agents to navigate uncertain environments while deconflicting trajectories and avoiding obstacles using perception information. PARM* differs from PARM as it is less conservative, using more computation to find closer-to-optimal solutions. While these methods achieve state-of-the-art performance, they suffer from high computational costs as they need to solve large optimization problems onboard, making it difficult for agents to replan at high rates. To overcome this challenge, we present our second key contribution, PRIMER, a learning-based planner trained with imitation learning (IL) using PARM* as the expert demonstrator. PRIMER leverages the low computational requirements at deployment of neural networks and achieves a computation speed up to 5500 times faster than optimization-based approaches.