Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation
Keywords: Model Predictive Control, Transformers, Performers, Highly-Constrained Navigation, Social Navigation, Learning-based Control
Abstract: Despite decades of research, existing navigation systems still face real-world challenges when deployed in the wild, e.g., in cluttered home environments or in human-occupied public spaces.
To address this, we present a new class of implicit control policies combining the benefits of imitation learning with the robust handling of system constraints from Model Predictive Control (MPC).
Our approach, called Performer-MPC, uses a learned cost function parameterized by vision context embeddings provided by Performers---a low-rank implicit-attention Transformer. We jointly train the cost function and construct the controller relying on it, effectively solving end-to-end the corresponding bi-level optimization problem.
We show that the resulting policy improves standard MPC performance by leveraging a few expert demonstrations of the desired navigation behavior in different challenging real-world scenarios.
Compared with a standard MPC policy, Performer-MPC achieves >40% better goal reached in cluttered environments and >65% better on social metrics when navigating around humans.
Student First Author: no
Supplementary Material: zip
Website: https://performermpc.github.io/
8 Replies
Loading