Towards Bio-Inspired Robotic Trajectory Planning via Self-Supervised RNN
This work addresses trajectory planning for robotics, offering a potentially adaptive solution for complex manipulation tasks, though it appears incremental as it builds on existing supervised sequence learning approaches.
The paper tackled robotic trajectory planning by proposing a self-supervised recurrent neural network that learns to generate trajectories using forward and inverse kinematics models, showing feasibility for kinematic planning tasks without requiring imitation of observed trajectories.
Trajectory planning in robotics is understood as generating a sequence of joint configurations that will lead a robotic agent, or its manipulator, from an initial state to the desired final state, thus completing a manipulation task while considering constraints like robot kinematics and the environment. Typically, this is achieved via sampling-based planners, which are computationally intensive. Recent advances demonstrate that trajectory planning can also be performed by supervised sequence learning of trajectories, often requiring only a single or fixed number of passes through a neural architecture, thus ensuring a bounded computation time. Such fully supervised approaches, however, perform imitation learning; they do not learn based on whether the trajectories can successfully reach a goal, but try to reproduce observed trajectories. In our work, we build on this approach and propose a cognitively inspired self-supervised learning scheme based on a recurrent architecture for building a trajectory model. We evaluate the feasibility of the proposed method on a task of kinematic planning for a robotic arm. The results suggest that the model is able to learn to generate trajectories only using given paired forward and inverse kinematics models, and indicate that this novel method could facilitate planning for more complex manipulation tasks requiring adaptive solutions.