Abstract

Visual anticipation of ego and object motion over a short time horizons is a key feature of human-level performance in complex environments. We propose a driving policy learning framework that predicts feature representations of future visual inputs; our predictive model infers not only future events but also semantics, which provide a visual explanation of policy decisions. Our Semantic Predictive Control (SPC) framework predicts future semantic segmentation and events by aggregating multi-scale feature maps. A guidance model assists action selection and enables efficient sampling-based optimization. Experiments on multiple simulation environments show that networks which implement SPC can outperform existing model-based reinforcement learning algorithms in terms of data efficiency and total rewards while providing clear explanations for the policy’s behavior.

Video

Paper

Xinlei Pan, Xiangyu Chen, Qizhi Cai, John Canny, Fisher Yu Semantic Predictive Control for Explainable and Efficient Policy Learning ICRA 2019

Code

github.com/ucbdrive/spc

Citation

@inproceedings{pan2019semantic,
  title={Semantic predictive control for explainable and efficient policy learning},
  author={Pan, Xinlei and Chen, Xiangyu and Cai, Qizhi and Canny, John and Yu, Fisher},
  booktitle={2019 International Conference on Robotics and Automation (ICRA)},
  pages={3203--3209},
  year={2019},
  organization={IEEE}
}