# Learning by Watching

arXiv: https://arxiv.org/abs/2106.05966 · HTML: https://mlsanity.com/paper/2106.05966/

## Key facts

- Cited by 22 papers in the map (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 54 of its 80 references that are in the map.
- First posted on arXiv 10 Jun 2021.

## 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, 30 of 54)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints](https://mlsanity.com/paper/1806.01482/) (2018)
- [End-to-end Interpretable Neural Motion Planner](https://mlsanity.com/paper/2101.06679/) (2021)
- [One Thousand and One Hours: Self-driving Motion Prediction Dataset](https://mlsanity.com/paper/2006.14480/) (2020)
- [Human Motion Trajectory Prediction: A Survey](https://mlsanity.com/paper/1905.06113/) (2019)
- [DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving](https://mlsanity.com/paper/1505.00256/) (2015)
- [Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks](https://mlsanity.com/paper/1907.03395/) (2019)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)
- [Cross-view Semantic Segmentation for Sensing Surroundings](https://mlsanity.com/paper/1906.03560/) (2019)
- [Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation](https://mlsanity.com/paper/1707.03374/) (2017)
- [IntentNet: Learning to Predict Intention from Raw Sensor Data](https://mlsanity.com/paper/2101.07907/) (2021)
- [End-to-End Model-Free Reinforcement Learning for Urban Driving using Implicit Affordances](https://mlsanity.com/paper/1911.10868/) (2019)
- [PnPNet: End-to-End Perception and Prediction with Tracking in the Loop](https://mlsanity.com/paper/2005.14711/) (2020)
- [Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?](https://mlsanity.com/paper/2006.14911/) (2020)
- [Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions](https://mlsanity.com/paper/1906.08945/) (2019)
- [Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data](https://mlsanity.com/paper/1910.08233/) (2019)
- [Third-Person Imitation Learning](https://mlsanity.com/paper/1703.01703/) (2017)

## Built on by (most cited first, 22 of 22)

- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [EMMA: End-to-End Multimodal Model for Autonomous Driving](https://mlsanity.com/paper/2410.23262/) (2024)
- [Learning from All Vehicles](https://mlsanity.com/paper/2203.11934/) (2022)
- [PlanT: Explainable Planning Transformers via Object-Level Representations](https://mlsanity.com/paper/2210.14222/) (2022)
- [Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Survey](https://mlsanity.com/paper/2307.04370/) (2023)
- [Coaching a Teachable Student](https://mlsanity.com/paper/2306.10014/) (2023)
- [SelfD: Self-Learning Large-Scale Driving Policies From the Web](https://mlsanity.com/paper/2204.10320/) (2022)
- [XVO: Generalized Visual Odometry via Cross-Modal Self-Training](https://mlsanity.com/paper/2309.16772/) (2023)
- [Safe Autonomous Racing via Approximate Reachability on Ego-vision](https://mlsanity.com/paper/2110.07699/) (2021)
- [Adversarial Imitation Learning from Visual Observations using Latent Information](https://mlsanity.com/paper/2309.17371/) (2023)
- [Learning by Watching: A Review of Video-based Learning Approaches for Robot Manipulation](https://mlsanity.com/paper/2402.07127/) (2024)
- [On the Road to Portability: Compressing End-to-End Motion Planner for Autonomous Driving](https://mlsanity.com/paper/2403.01238/) (2024)
- [Causal Imitative Model for Autonomous Driving](https://mlsanity.com/paper/2112.03908/) (2021)
- [Fully Unified Motion Planning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2504.12667/) (2025)
- [Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing](https://mlsanity.com/paper/2205.02953/) (2022)
- [AutoGraph: Predicting Lane Graphs from Traffic Observations](https://mlsanity.com/paper/2306.15410/) (2023)
- [Trajectory Planning for Autonomous Driving in Unstructured Scenarios Based on Graph Neural Network and Numerical Optimization](https://mlsanity.com/paper/2406.08855/) (2024)
- [Designed to Cooperate: A Kant-Inspired Ethic of Machine-to-Machine Cooperation](https://mlsanity.com/paper/2109.13493/) (2021)
- [Learning to Drive by Imitating Surrounding Vehicles](https://mlsanity.com/paper/2503.05997/) (2025)
- [Mirror Learning](https://mlsanity.com/paper/2607.28737/) (2026)
- [SkyDrive: Learning to Drive in a New City from Aerial Traffic Monitoring](https://mlsanity.com/paper/2608.25142/) (2026)

## Abstract (arXiv)

When in a new situation or geographical location, human drivers have an extraordinary ability to watch others and learn maneuvers that they themselves may have never performed. In contrast, existing techniques for learning to drive preclude such a possibility as they assume direct access to an instrumented ego-vehicle with fully known observations and expert driver actions. However, such measurements cannot be directly accessed for the non-ego vehicles when learning by watching others. Therefore, in an application where data is regarded as a highly valuable asset, current approaches completely discard the vast portion of the training data that can be potentially obtained through indirect observation of surrounding vehicles. Motivated by this key insight, we propose the Learning by Watching (LbW) framework which enables learning a driving policy without requiring full knowledge of neither the state nor expert actions. To increase its data, i.e., with new perspectives and maneuvers, LbW makes use of the demonstrations of other vehicles in a given scene by (1) transforming the ego-vehicle's observations to their points of view, and (2) inferring their expert actions. Our LbW agent learns more robust driving policies while enabling data-efficient learning, including quick adaptation of the policy to rare and novel scenarios. In particular, LbW drives robustly even with a fraction of available driving data required by existing methods, achieving an average success rate of 92% on the original CARLA benchmark with only 30 minutes of total driving data and 82% with only 10 minutes.