.png){kind=icon}
Return
Anticipating interactions: a predictive diffusion framework for evolving bimanual manipulation
.png){kind=icon}
OA
AI
DOI：10.3389/fnbot.2026.1927097.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
IntroductionBimanual robotic manipulation remains a significant challenge in embodied AI, as it requires synchronized motion planning, inter-arm collision avoidance, and dynamic role allocation over long task horizons. Although existing diffusion-based policies and affordance learning methods have demonstrated considerable capability, they largely treat the environment as static and fail to model how interaction relationships and coordination patterns evolve over time.MethodsThis paper introduces the Predictive Affordance and Coordination Evolution Diffusion Policy (PACE-DP), a unified framework that explicitly forecasts future scene dynamics and models the temporal progression of manipulation affordances and bimanual coordination. PACE-DP integrates three predictive components: (1) a Predictive Scene Module that forecasts latent future object-centric representations; (2) an Affordance and Coordination Evolution Module that constructs temporally evolving interaction graphs and employs a Graph Transformer to predict future relation types, grasp success probabilities, coordination modes, and spatial alignment targets; and (3) a Conditional Diffusion Policy that generates smooth, coordinated action sequences conditioned on fused current and predicted features.ResultsWe evaluate PACE-DP on the RoboTwin 2.0 platform across 10 diverse bimanual tasks, including handover, placement, stacking, and switch operation. Experimental results show that PACE-DP performs favorably compared with baseline methods, achieving higher success rates on coordination-intensive tasks with only marginal computational overhead.DiscussionThese findings suggest that explicitly predicting future affordance and coordination evolution provides an effective inductive bias for bimanual manipulation, enabling more reliable coordination without substantially increasing computational cost. PACE-DP thus offers a promising step toward predictive, temporally aware policies for long-horizon bimanual tasks.
Keywords:
bimanual manipulation,diffusion policy,affordance learning,Graph Transformer,predictive scene modeling
Journal
IF:
2.8
Papers:
175
Citations:
4.1K
Organization
Cited Papers
No cited papers available