Motion Planning Networks
This addresses the problem of slow motion planning for robotics applications like self-driving cars, offering a novel method that is incremental in its neural network approach.
The paper tackles the exponential computational complexity of motion planning in high-dimensional robotics by proposing Motion Planning Networks (MPNet), a neural network-based algorithm that encodes workspaces from point clouds to generate collision-free paths. Results show MPNet is computationally efficient, generalizes to unseen environments, and consistently achieves computation times under 1 second, significantly outperforming state-of-the-art methods.
Fast and efficient motion planning algorithms are crucial for many state-of-the-art robotics applications such as self-driving cars. Existing motion planning methods become ineffective as their computational complexity increases exponentially with the dimensionality of the motion planning problem. To address this issue, we present Motion Planning Networks (MPNet), a neural network-based novel planning algorithm. The proposed method encodes the given workspaces directly from a point cloud measurement and generates the end-to-end collision-free paths for the given start and goal configurations. We evaluate MPNet on various 2D and 3D environments including the planning of a 7 DOF Baxter robot manipulator. The results show that MPNet is not only consistently computationally efficient in all environments but also generalizes to completely unseen environments. The results also show that the computation time of MPNet consistently remains less than 1 second in all presented experiments, which is significantly lower than existing state-of-the-art motion planning algorithms.