Leveraging Scene Embeddings for Gradient-Based Motion Planning in Latent Space
This work addresses the problem of real-world applicability for motion planning in robotics, though it appears incremental by building on existing latent space optimization methods.
The paper tackled the challenge of applying latent space motion planning to complex real-world scenes by using learned scene embeddings and a generative robot model, achieving an order of magnitude faster computation speed than traditional methods and enabling real-time closed-loop planning.
Motion planning framed as optimisation in structured latent spaces has recently emerged as competitive with traditional methods in terms of planning success while significantly outperforming them in terms of computational speed. However, the real-world applicability of recent work in this domain remains limited by the need to express obstacle information directly in state-space, involving simple geometric primitives. In this work we address this challenge by leveraging learned scene embeddings together with a generative model of the robot manipulator to drive the optimisation process. In addition, we introduce an approach for efficient collision checking which directly regularises the optimisation undertaken for planning. Using simulated as well as real-world experiments, we demonstrate that our approach, AMP-LS, is able to successfully plan in novel, complex scenes while outperforming traditional planning baselines in terms of computation speed by an order of magnitude. We show that the resulting system is fast enough to enable closed-loop planning in real-world dynamic scenes.