GPU Accelerated Batch Multi-Convex Trajectory Optimization for a Rectangular Holonomic Mobile Robot

TL;DR

This paper introduces a GPU-accelerated batch trajectory optimization method for holonomic mobile robots that improves solution quality and computational speed by leveraging multi-convex reformulation and batch processing.

Contribution

The paper presents a novel batch optimization algorithm that enhances trajectory planning for holonomic robots by reformulating constraints and exploiting GPU acceleration, outperforming existing methods.

Findings

Achieves real-time batch trajectory optimization for hundreds of instances.

Outperforms baseline and cross-entropy methods in solution quality.

Significantly faster than parallel CPU approaches.

Abstract

We present a batch trajectory optimizer that can simultaneously solve hundreds of different instances of the problem in real-time. We consider holonomic robots but relax the assumption of circular base footprint. Our main algorithmic contributions lie in: (i) improving the computational tractability of the underlying non-convex problem and (ii) leveraging batch computation to mitigate initialization bottlenecks and improve solution quality. We achieve both goals by deriving a multi-convex reformulation of the kinematics and collision avoidance constraints. We exploit these structures through an Alternating Minimization approach and show that the resulting batch operation reduces to computing just matrix-vector products that can be trivially accelerated over GPUs. We improve the state-of-the-art in three respects. First, we improve quality of navigation (success-rate, tracking) as compared to baseline approach that relies on computing a single locally optimal trajectory at each control loop. Second, we show that when initialized with trajectory samples from a Gaussian distribution, our batch optimizer outperforms state-of-the-art cross-entropy method in solution quality. Finally, our batch optimizer is several orders of magnitude faster than the conceptually simpler alternative of running different optimization instances in parallel CPU threads. \textbf{Codes:} \url{https://tinyurl.com/a3b99m8}