Diffusion-based Planning with Learned Viability Filters
This work addresses motion planning for robotics and human locomotion by improving constraint satisfaction in diffusion models, though it is incremental as it builds on existing diffusion planning methods.
The paper tackles the problem of diffusion-based motion planning failing to satisfy hard constraints like avoiding falls or collisions by proposing learned viability filters that predict future success of plans, enabling online planning for 3D human locomotion tasks such as box-climbing and obstacle avoidance, with results showing it is significantly faster than guidance-based diffusion prediction.
Diffusion models can be used as a motion planner by sampling from a distribution of possible futures. However, the samples may not satisfy hard constraints that exist only implicitly in the training data, e.g., avoiding falls or not colliding with a wall. We propose learned viability filters that efficiently predict the future success of any given plan, i.e., diffusion sample, and thereby enforce an implicit future-success constraint. Multiple viability filters can also be composed together. We demonstrate the approach on detailed footstep planning for challenging 3D human locomotion tasks, showing the effectiveness of viability filters in performing online planning and control for box-climbing, step-over walls, and obstacle avoidance. We further show that using viability filters is significantly faster than guidance-based diffusion prediction.