LARVO-RRT*: Learning Guided Adaptive Reconfiguration with Vector Field Oriented RRT*
Wijenayaka Kankanamge Rishan Sachinthana, Bhagya Prasangi Samarakoon Samarakoon Mudiyanselage, Viraj Jagathpriya Muthugala Muthugala Arachchige, Mohan Rajesh Elara
AI summary
Problem
Fixed-shape robots cannot navigate narrow passages, and traditional sampling-based planners like RRT* consume excessive computation and memory while converging slowly in complex environments.
Approach
A U-Net-based CNN jointly predicts path probability maps, dense flow fields, and feasible robot configurations to guide biased sampling and steering within a modified RRT* framework.
Key results
- Reduces planning time and iteration counts versus baselines
- Improves path optimality and quality in complex maps
- Enables navigation through narrow passages via adaptive shape reconfiguration
- Maintains probabilistic completeness by blending neural guidance with uniform sampling
Why it matters
Enables efficient, optimal navigation for modular reconfigurable robots in constrained environments, advancing autonomous exploration and deployment.
Abstract
Path planning is a challenging problem in robotics, for which numerous algorithms have been developed to address it. Sampling-based algorithms, such as the Rapidly Exploring Random Tree (RRT) and its variants, are renowned for their ability to explore the search space efficiently. However, these algorithms consume a considerable amount of computation time and memory to derive the optimal path. Furthermore, when it comes to different geometrical factors, such as narrow passages, fixed-shape robots often fail to navigate because of their structural constraints. This limitation raises the need to use reconfigurable robots, which are capable of changing their shape to access these confined areas. This paper proposes a novel path planning approach for a reconfigurable robot, based on a machine learning model, to address the aforementioned limitations. The proposed method employs a Convolutional Neural Network (CNN) model that predicts sample distribution, a flow field, and robot configurations, which is combined with RRT*, termed Learning Guided Adaptive Reconfiguration with Vector Field Oriented RRT* (LARVO-RRT*). The model has been trained using the optimal sample distributions and flow fields generated with the help of optimal paths from a cus- tomized A* algorithm. Experimental results demonstrate that the proposed method surpasses the existing learning and non- learning-based path planning algorithms in terms of time cost, iteration count, and path quality. Furthermore, the algorithm has been able to outperform the existing path planners even without considering the reconfigurations.