Skip to main navigation Skip to search Skip to main content

BRIC: Bridging Kinematic Plans and Physical Control at Test Time

  • Dohun Lim
  • , Minji Kim
  • , Jaewoon Lim
  • , Sungchan Kim*
  • *Corresponding author for this work
  • Jeonbuk National University

Research output: Contribution to journalConference articlepeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)23505-23513
Number of pages9
JournalProceedings of the AAAI Conference on Artificial Intelligence
Volume40
Issue number28
DOIs
StatePublished - 2026
Event40th AAAI Conference on Artificial Intelligence, AAAI 2026 - Singapore, Singapore
Duration: 2026.01.202026.01.27

Fingerprint

Dive into the research topics of 'BRIC: Bridging Kinematic Plans and Physical Control at Test Time'. Together they form a unique fingerprint.

Cite this