Spatio-Temporal Retrieval-based Priors for Adaptive Computational Teaching in Driving
This work addresses the need for adaptive coaching systems in high-performance driving, a domain where long-term student-teacher interactions are critical, but the results are incremental given the use of existing imitation learning and retrieval techniques.
The paper tackles the problem of adaptive computational teaching for complex motor tasks like high-performance driving, where existing systems fail to account for long-term student learning. The proposed imitation learning model with a temporal reasoning module and nearest neighbor retrieval prior consistently outperforms non-adaptive and alternative adaptive baselines on both semi-synthetic and real-world driving coaching datasets.
Learning-based automated coaching systems for complex motor tasks such as high-performance driving remain limited in the ability to be adaptive by their reliance only on local, context-dependent reasoning, failing to account for the long-term temporal nature of student learning and the cumulative impact of repeated teacher-student interactions. In this paper, we propose an imitation learning based computational model for adaptive teaching with a dedicated temporal reasoning module that can reason over the interaction history under low-data regimes. To compensate for limited amounts of interactive training data, and based on the repetitive nature of the teaching process, the model relies on a nearest neighbor retrieval and cross attention prior, reasoning only on a narrowed-down set of semantically similar past interactions with an encoder-decoder based concurrent teaching model. We validate our approach with (i) a novel semi-synthetic closed-loop longitudinal student-teacher interaction dataset based on Waymo Open Motion Dataset and (ii) a small-scale real-world naturalistic simulator race coaching dataset. Our results reveal the consistent advantage of our adaptive teaching model with the nearest neighbor retrieval and cross-attention prior over a non-adaptive baseline as well as a suite of adaptive models that differ in their choice of priors and temporal fusion mechanisms.