BRIC: Bridging Kinematic Plans and Physical Control at Test Time
This addresses execution drift in human motion generation for robotics or animation, though it is incremental as it builds on existing diffusion and reinforcement learning methods.
They tackled the problem of physically implausible motions from diffusion-based planners in long-term human motion generation by proposing BRIC, a test-time adaptation framework that dynamically adapts physics controllers and guides diffusion models, achieving state-of-the-art performance across tasks like motion composition and obstacle avoidance.
We propose BRIC, a novel test-time adaptation (TTA) framework that enables long-term human motion generation by resolving execution discrepancies between diffusion-based kinematic motion planners and reinforcement learning-based physics controllers. While diffusion models can generate diverse and expressive motions conditioned on text and scene context, they often produce physically implausible outputs, leading to execution drift during simulation. To address this, BRIC dynamically adapts the physics controller to noisy motion plans at test time, while preserving pre-trained skills via a loss function that mitigates catastrophic forgetting. In addition, BRIC introduces a lightweight test-time guidance mechanism that steers the diffusion model in the signal space without updating its parameters. By combining both adaptation strategies, BRIC ensures consistent and physically plausible long-term executions across diverse environments in an effective and efficient manner. We validate the effectiveness of BRIC on a variety of long-term tasks, including motion composition, obstacle avoidance, and human-scene interaction, achieving state-of-the-art performance across all tasks.