# How To Not Drive: Learning Driving Constraints from Demonstration

arXiv: https://arxiv.org/abs/2110.00645 · HTML: https://mlsanity.com/paper/2110.00645/

## Key facts

- Cited by 2 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 16 of its 25 references that are in the map.
- First posted on arXiv 1 Oct 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, 16 of 16)

- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [End-to-end Interpretable Neural Motion Planner](https://mlsanity.com/paper/2101.06679/) (2021)
- [MP3: A Unified Model to Map, Perceive, Predict and Plan](https://mlsanity.com/paper/2101.06806/) (2021)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Multi-Agent Imitation Learning for Driving Simulation](https://mlsanity.com/paper/1803.01044/) (2018)
- [Inverse Constrained Reinforcement Learning](https://mlsanity.com/paper/2011.09999/) (2020)
- [Modeling Human Driving Behavior through Generative Adversarial Imitation Learning](https://mlsanity.com/paper/2006.06412/) (2020)
- [Maximum Likelihood Constraint Inference for Inverse Reinforcement Learning](https://mlsanity.com/paper/1909.05477/) (2019)
- [Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving](https://mlsanity.com/paper/2006.13704/) (2020)
- [End-to-end Multi-Modal Multi-Task Vehicle Control for Self-Driving Cars with Visual Perception](https://mlsanity.com/paper/1801.06734/) (2018)
- [Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving](https://mlsanity.com/paper/2011.01153/) (2020)
- [Deep Inverse Q-learning with Constraints](https://mlsanity.com/paper/2008.01712/) (2020)
- [Learning Safe Policies with Expert Guidance](https://mlsanity.com/paper/1805.08313/) (2018)
- [Learning Constraints from Demonstrations](https://mlsanity.com/paper/1812.07084/) (2018)
- [Planning on the fast lane: Learning to interact using attention mechanisms in path integral inverse reinforcement learning](https://mlsanity.com/paper/2007.05798/) (2020)

## Built on by (most cited first, 2 of 2)

- [Learning Safety Constraints from Demonstrations with Unknown Rewards](https://mlsanity.com/paper/2305.16147/) (2023)
- [Quantification of Actual Road User Behavior on the Basis of Given Traffic Rules](https://mlsanity.com/paper/2202.09269/) (2022)

## Abstract (arXiv)

We propose a new scheme to learn motion planning constraints from human driving trajectories. Behavioral and motion planning are the key components in an autonomous driving system. The behavioral planning is responsible for high-level decision making required to follow traffic rules and interact with other road participants. The motion planner role is to generate feasible, safe trajectories for a self-driving vehicle to follow. The trajectories are generated through an optimization scheme to optimize a cost function based on metrics related to smoothness, movability, and comfort, and subject to a set of constraints derived from the planned behavior, safety considerations, and feasibility. A common practice is to manually design the cost function and constraints. Recent work has investigated learning the cost function from human driving demonstrations. While effective, the practical application of such approaches is still questionable in autonomous driving. In contrast, this paper focuses on learning driving constraints, which can be used as an add-on module to existing autonomous driving solutions. To learn the constraint, the planning problem is formulated as a constrained Markov Decision Process, whose elements are assumed to be known except the constraints. The constraints are then learned by learning the distribution of expert trajectories and estimating the probability of optimal trajectories belonging to the learned distribution. The proposed scheme is evaluated using NGSIM dataset, yielding less than 1% collision rate and out of road maneuvers when the learned constraints is used in an optimization-based motion planner.