SEB-Naver: A SE(2)-based Local Navigation Framework for Car-like Robots on Uneven Terrain

2025-03-04

AI Summary

Addressing two key challenges in autonomous navigation of car-like robots over unstructured, rugged terrain—namely, inaccurate traversability assessment and difficulty in modeling terrain-coupled kinematics—this paper proposes: (1) a real-time traversability evaluation method based on SE(2) grids, enabling millisecond-scale terrain understanding; and (2) a heuristic trajectory optimization framework that integrates terrain-aware kinematic modeling with differential flatness, supporting optimization-driven local replanning. Leveraging GPU-accelerated parallel computation and real-time local map construction, the system significantly improves traversal success rate and trajectory smoothness in both simulation and real-world off-road environments. To the best of our knowledge, this work achieves the first closed-loop, real-time, and highly robust autonomous navigation for car-like robots on rugged terrain.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Autonomous navigation of car-like robots on uneven terrain poses unique challenges compared to flat terrain, particularly in traversability assessment and terrain-associated kinematic modelling for motion planning. This paper introduces SEB-Naver, a novel SE(2)-based local navigation framework designed to overcome these challenges. First, we propose an efficient traversability assessment method for SE(2) grids, leveraging GPU parallel computing to enable real-time updates and maintenance of local maps. Second, inspired by differential flatness, we present an optimization-based trajectory planning method that integrates terrain-associated kinematic models, significantly improving both planning efficiency and trajectory quality. Finally, we unify these components into SEB-Naver, achieving real-time terrain assessment and trajectory optimization. Extensive simulations and real-world experiments demonstrate the effectiveness and efficiency of our approach. The code is at https://github.com/ZJU-FAST-Lab/seb_naver.

Problem

• Autonomous navigation for car-like robots on uneven terrain.
• Real-time traversability assessment using SE(2) grids and GPU computing.
• Optimization-based trajectory planning integrating terrain kinematic models.

Innovation

• GPU parallel computing for real-time map updates
• Optimization-based trajectory planning using differential flatness
• Integration of terrain-associated kinematic models