# Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks

arXiv: https://arxiv.org/abs/1811.02759 · HTML: https://mlsanity.com/paper/1811.02759/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2018.

## Built on by (most cited first, 19 of 19)

- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [End-to-End Urban Driving by Imitating a Reinforcement Learning Coach](https://mlsanity.com/paper/2108.08265/) (2021)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [SCPNet: Semantic Scene Completion on Point Cloud](https://mlsanity.com/paper/2303.06884/) (2023)
- [Positional Encoder Graph Neural Networks for Geographic Data](https://mlsanity.com/paper/2111.10144/) (2021)
- [SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation](https://mlsanity.com/paper/2506.17290/) (2025)
- [Network Pruning via Resource Reallocation](https://mlsanity.com/paper/2103.01847/) (2021)
- [Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems](https://mlsanity.com/paper/2104.04000/) (2021)
- [Autonomous Catheterization with Open-source Simulator and Expert Trajectory](https://mlsanity.com/paper/2401.09059/) (2024)
- [Multi-Modal Fusion for Sensorimotor Coordination in Steering Angle Prediction](https://mlsanity.com/paper/2202.05500/) (2022)
- [An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty](https://mlsanity.com/paper/2212.06828/) (2022)
- [CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks](https://mlsanity.com/paper/2205.08712/) (2022)
- [KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Tasks](https://mlsanity.com/paper/2305.14644/) (2023)
- [Model-Driven Deep Neural Network for Enhanced AoA Estimation Using 5G gNB](https://mlsanity.com/paper/2501.00009/) (2024)
- [Vision-Guided Forecasting -- Visual Context for Multi-Horizon Time Series Forecasting](https://mlsanity.com/paper/2107.12674/) (2021)
- [LW-ISP: A Lightweight Model with ISP and Deep Learning](https://mlsanity.com/paper/2210.03904/) (2022)
- [P2Seg: Pointly-supervised Segmentation via Mutual Distillation](https://mlsanity.com/paper/2401.09709/) (2024)
- [UniPlanner: A Unified Motion Planning Framework for Autonomous Vehicle Decision-Making Systems via Multi-Dataset Integration](https://mlsanity.com/paper/2510.24166/) (2025)

## Abstract (arXiv)

The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, these methods are susceptible to the presence of sharp road curves, challenging traffic conditions, strong shadows, and severe lighting changes. In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction. Specifically, we train our steering angle predictive model by distilling multi-layer knowledge from multiple heterogeneous auxiliary networks that perform related but different tasks, e.g., image segmentation or optical flow estimation. As opposed to multi-task learning, our method does not require expensive annotations of related tasks on the target set. This is made possible by applying contemporary off-the-shelf networks on the target set and mimicking their features in different layers after transformation. The auxiliary networks are discarded after training without affecting the runtime efficiency of our model. Our approach achieves a new state-of-the-art on Udacity and Comma.ai, outperforming the previous best by a large margin of 12.8% and 52.1%, respectively. Encouraging results are also shown on Berkeley Deep Drive (BDD) dataset.