ColorDynamic: Generalizable, Scalable, Real-time, End-to-end Local Planner for Unstructured and Dynamic Environments

TL;DR

ColorDynamic introduces a real-time, end-to-end DRL-based local planner for unstructured and dynamic environments, featuring a novel network, scalable training platform, and demonstrated high success rates in complex scenarios.

Contribution

The paper presents the ColorDynamic framework with Transqer network, E-Sparrow simulation platform, and data augmentation, advancing DRL-based local planning in unstructured, dynamic environments.

Findings

Achieves over 90% success rate in complex scenarios.

Operates in real-time with 1.2-1.3 ms planning time.

Demonstrates superior performance in simulated and real-world tests.

Abstract

Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments. To address these challenges, this study proposes the ColorDynamic framework. First, an end-to-end DRL formulation is established, which maps raw sensor data directly to control commands, thereby ensuring compatibility with unstructured environments. Under this formulation, a novel network, Transqer, is introduced. The Transqer enables online DRL learning from temporal transitions, substantially enhancing decision-making in dynamic scenarios. To facilitate scalable training of Transqer with diverse data, an efficient simulation platform E-Sparrow, along with a data augmentation technique leveraging symmetric invariance, are developed. Comparative evaluations against state-of-the-art methods, alongside assessments of generalizability, scalability, and real-time performance, were conducted to validate the effectiveness of ColorDynamic. Results indicate that our approach achieves a success rate exceeding 90% while exhibiting real-time capacity (1.2-1.3 ms per planning). Additionally, ablation studies were performed to corroborate the contributions of individual components. Building on this, the OkayPlan-ColorDynamic (OPCD) navigation system is presented, with simulated and real-world experiments demonstrating its superiority and applicability in complex scenarios. The codebase and experimental demonstrations have been open-sourced on our website to facilitate reproducibility and further research.