# Spatio-Temporal Retrieval-based Priors for Adaptive Computational Teaching in Driving

arXiv: https://arxiv.org/abs/2606.25224 · HTML: https://mlsanity.com/paper/2606.25224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 23 Jun 2026.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)

## Builds on (most cited first, 24 of 24)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [Deep Knowledge Tracing](https://mlsanity.com/paper/1506.05908/) (2015)
- [DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets](https://mlsanity.com/paper/2108.09640/) (2021)
- [Dynamic Key-Value Memory Networks for Knowledge Tracing](https://mlsanity.com/paper/1611.08108/) (2016)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [EdNet: A Large-Scale Hierarchical Dataset in Education](https://mlsanity.com/paper/1912.03072/) (2019)
- [Hierarchical Multiscale Recurrent Neural Networks](https://mlsanity.com/paper/1609.01704/) (2016)
- [Hierarchical Imitation and Reinforcement Learning](https://mlsanity.com/paper/1803.00590/) (2018)
- [DAISI: Database for AI Surgical Instruction](https://mlsanity.com/paper/2004.02809/) (2020)
- [Assistive Teaching of Motor Control Tasks to Humans](https://mlsanity.com/paper/2211.14003/) (2022)
- [COACH: Cooperative Robot Teaching](https://mlsanity.com/paper/2302.06199/) (2023)
- [Computational Teaching for Driving via Multi-Task Imitation Learning](https://mlsanity.com/paper/2410.01608/) (2024)
- [Hierarchical Variational Imitation Learning of Control Programs](https://mlsanity.com/paper/1912.12612/) (2019)
- [Generating Language Corrections for Teaching Physical Control Tasks](https://mlsanity.com/paper/2306.07012/) (2023)
- [Shared Autonomy for Proximal Teaching](https://mlsanity.com/paper/2502.19899/) (2025)
- [Ongoing Tracking of Engagement in Motor Learning](https://mlsanity.com/paper/2308.07670/) (2023)
- [Skill-informed Data-driven Haptic Nudges for High-dimensional Human Motor Learning](https://mlsanity.com/paper/2603.12583/) (2026)

## Abstract (arXiv)

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.