Transformer-Enhanced Motion Planner: Attention-Guided Sampling for State-Specific Decision Making

Abstract

Sampling-based motion planning (SBMP) algorithms are renowned for their robust global search capabilities. However, the inherent randomness in their sampling mechanisms often results in inconsistent path quality and limited search efficiency. In response to these challenges, this work proposes a novel deep learning-based motion planning framework, named Transformer-Enhanced Motion Planner (TEMP), which synergizes a Co-Regulation Environmental Information Encoder (CEIE) with a Motion Planning Transformer (MPT). CEIE converts scenario data into encoded environmental information (EEI), providing MPT with an insightful understanding of the environment. MPT leverages an attention mechanism to dynamically recalibrate its focus on EEI, task objectives, and historical planning data, refining the sampling node generation. To demonstrate the capabilities of TEMP, we train our model using a dataset consisting of planning results produced by RRT*. CEIE and MPT are collaboratively trained, enabling CEIE to autonomously learn and extract patterns from environmental data, thereby forming informative representations that MPT can more effectively interpret and utilize for motion planning. Subsequently, we systematically evaluate TEMP's efficacy across diverse dimensions and assess it in out-of-distribution real-world scenarios, demonstrating that TEMP achieves exceptional performance metrics and a heightened degree of generalizability compared to state-of-the-art SBMPs.