Topology-Guided ORCA: Smooth Multi-Agent Motion Planning in Constrained Environments

TL;DR

Topology-Guided ORCA enhances multi-agent motion planning in environments with static obstacles by integrating topology-aware path planning, resulting in smoother and more natural agent movements compared to traditional ORCA.

Contribution

The paper introduces a topology-guided extension to ORCA that effectively navigates static obstacles, improving multi-agent motion planning in constrained environments.

Findings

Outperforms ORCA in smoothness of agent motions

Generates more natural multi-agent behaviors in constrained spaces

Shows potential for training social navigation policies

Abstract

We present Topology-Guided ORCA as an alternative simulator to replace ORCA for planning smooth multi-agent motions in environments with static obstacles. Despite the impressive performance in simulating multi-agent crowd motion in free space, ORCA encounters a significant challenge in navigating the agents with the presence of static obstacles. ORCA ignores static obstacles until an agent gets too close to an obstacle, and the agent will get stuck if the obstacle intercepts an agent's path toward the goal. To address this challenge, Topology-Guided ORCA constructs a graph to represent the topology of the traversable region of the environment. We use a path planner to plan a path of waypoints that connects each agent's start and goal positions. The waypoints are used as a sequence of goals to guide ORCA. The experiments of crowd simulation in constrained environments show that our method outperforms ORCA in terms of generating smooth and natural motions of multiple agents in constrained environments, which indicates great potential of Topology-Guided ORCA for serving as an effective simulator for training constrained social navigation policies.