Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding
This addresses the problem of efficient motion planning in dynamic settings for robotics applications, representing a strong specific gain but not a paradigm shift.
The paper tackles motion planning in dynamic environments, such as multi-arm assembly and human-robot interaction, by proposing a GNN-based approach with temporal encoding and imitation learning, resulting in up to 95% faster planning and over 1000x reduction in collision checks while maintaining high success rates.
Learning-based methods have shown promising performance for accelerating motion planning, but mostly in the setting of static environments. For the more challenging problem of planning in dynamic environments, such as multi-arm assembly tasks and human-robot interaction, motion planners need to consider the trajectories of the dynamic obstacles and reason about temporal-spatial interactions in very large state spaces. We propose a GNN-based approach that uses temporal encoding and imitation learning with data aggregation for learning both the embeddings and the edge prioritization policies. Experiments show that the proposed methods can significantly accelerate online planning over state-of-the-art complete dynamic planning algorithms. The learned models can often reduce costly collision checking operations by more than 1000x, and thus accelerating planning by up to 95%, while achieving high success rates on hard instances as well.