Motion Planning Transformers: A Motion Planning Framework for Mobile Robots
This addresses the challenge of fast and efficient motion planning for mobile robots like autonomous cars, offering improved generalizability over existing methods, though it is incremental as it builds on learning-based approaches.
The paper tackles the problem of inefficient sampling-based motion planning for mobile robots, particularly non-holonomic systems, by introducing a transformer-based approach that learns to restrict search spaces from prior data, resulting in a 2-12 times reduction in search space nodes compared to traditional planners.
Fast and efficient sampling-based motion planning (SMP) is an integral component of many robotic systems, such as autonomous cars. A popular technique to improve the efficiency of these planners is to restrict search space in the planning domain. Existing algorithms define parametric functions to bound the search space, but these do not extend to non-holonomic robotic systems. Recent learning-based methods use a combination of convolutional and fully connected networks to encode the planning space. However, these methods are restricted to fixed map sizes, which are often not realistic in the real world. In this paper, we introduce a transformer-based approach, Motion Planning Transformer, to restrict the search space by learning to discern regions with a valid path from prior data. The model learns not only to restrict search spaces for simple 2D systems but also for non-holonomic robotic systems. We validate our method on various randomly generated environments with different map sizes and plan trajectories for a physical non-holonomic robot. We also provide a ROS2 plugin of our method for the Nav2 planning stack. The results show that our method reduces search space nodes by 2-12 times compared to traditional planners and has better generalizability than recent learning-based planners.