Incorporating Human Domain Knowledge into Large Scale Cost Function Learning
This work addresses motion planning for autonomous systems by enhancing learning with human priors, though it is incremental as it builds on existing inverse reinforcement learning methods.
The paper tackles the problem of learning cost functions for motion planning by incorporating human domain knowledge as pretraining, which improves robustness, obstacle boundary clarity, and handling of rare cases like stairs and slopes compared to purely data-driven methods.
Recent advances have shown the capability of Fully Convolutional Neural Networks (FCN) to model cost functions for motion planning in the context of learning driving preferences purely based on demonstration data from human drivers. While pure learning from demonstrations in the framework of Inverse Reinforcement Learning (IRL) is a promising approach, we can benefit from well informed human priors and incorporate them into the learning process. Our work achieves this by pretraining a model to regress to a manual cost function and refining it based on Maximum Entropy Deep Inverse Reinforcement Learning. When injecting prior knowledge as pretraining for the network, we achieve higher robustness, more visually distinct obstacle boundaries, and the ability to capture instances of obstacles that elude models that purely learn from demonstration data. Furthermore, by exploiting these human priors, the resulting model can more accurately handle corner cases that are scarcely seen in the demonstration data, such as stairs, slopes, and underpasses.