Intention-Aware Navigation in Crowds with Extended-Space POMDP Planning

TL;DR

This paper introduces an advanced POMDP-based navigation system that enables autonomous agents to efficiently and safely navigate dense crowds by controlling multiple degrees of freedom and utilizing multi-query motion planning as priors.

Contribution

It extends POMDP planning to control both speed and heading in real-time, using multi-query motion planning techniques for rapid roll-out policy generation in crowded environments.

Findings

Generated trajectories are safer and more efficient.

The approach outperforms previous methods in dense crowds.

Real-time control with extended degrees of freedom is feasible.

Abstract

This paper presents a hybrid online Partially Observable Markov Decision Process (POMDP) planning system that addresses the problem of autonomous navigation in the presence of multi-modal uncertainty introduced by other agents in the environment. As a particular example, we consider the problem of autonomous navigation in dense crowds of pedestrians and among obstacles. Popular approaches to this problem first generate a path using a complete planner (e.g., Hybrid A*) with ad-hoc assumptions about uncertainty, then use online tree-based POMDP solvers to reason about uncertainty with control over a limited aspect of the problem (i.e. speed along the path). We present a more capable and responsive real-time approach enabling the POMDP planner to control more degrees of freedom (e.g., both speed AND heading) to achieve more flexible and efficient solutions. This modification greatly extends the region of the state space that the POMDP planner must reason over, significantly increasing the importance of finding effective roll-out policies within the limited computational budget that real time control affords. Our key insight is to use multi-query motion planning techniques (e.g., Probabilistic Roadmaps or Fast Marching Method) as priors for rapidly generating efficient roll-out policies for every state that the POMDP planning tree might reach during its limited horizon search. Our proposed approach generates trajectories that are safe and significantly more efficient than the previous approach, even in densely crowded dynamic environments with long planning horizons.