Edge Accelerated Robot Navigation With Collaborative Motion Planning

TL;DR

This paper introduces EARN, a collaborative motion planning framework that enables low-cost robots to perform real-time, collision-free navigation by dynamically switching between safety and efficiency modes under resource constraints.

Contribution

EARN is the first to integrate model predictive switching with bilevel optimization for resource-aware, real-time robot navigation in cluttered environments.

Findings

EARN reduces navigation time significantly.

EARN achieves higher success rates than existing methods.

Validated in indoor, outdoor, and real-world tests.

Abstract

Low-cost distributed robots suffer from limited onboard computing power, resulting in excessive computation time when navigating in cluttered environments. This paper presents Edge Accelerated Robot Navigation (EARN), to achieve real-time collision avoidance by adopting collaborative motion planning (CMP). As such, each robot can dynamically switch between a conservative motion planner executed locally to guarantee safety (e.g., path-following) and an aggressive motion planner executed non-locally to guarantee efficiency (e.g., overtaking). In contrast to existing motion planning approaches that ignore the interdependency between low-level motion planning and high-level resource allocation, EARN adopts model predictive switching (MPS) that maximizes the expected switching gain with respect to robot states and actions under computation and communication resource constraints. The MPS problem is solved by a tightly-coupled decision making and motion planning framework based on bilevel mixed-integer nonlinear programming and penalty dual decomposition. We validate the performance of EARN in indoor simulation, outdoor simulation, and real-world environments. Experiments show that EARN achieves significantly smaller navigation time and higher success rates than state-of-the-art navigation approaches.