Log In Sign Up

Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?

by   Angelos Filos, et al.

Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment, typically leading to arbitrary deductions and poorly-informed decisions. In principle, detection of and adaptation to OOD scenes can mitigate their adverse effects. In this paper, we highlight the limitations of current approaches to novel driving scenes and propose an epistemic uncertainty-aware planning method, called robust imitative planning (RIP). Our method can detect and recover from some distribution shifts, reducing the overconfident and catastrophic extrapolations in OOD scenes. If the model's uncertainty is too great to suggest a safe course of action, the model can instead query the expert driver for feedback, enabling sample-efficient online adaptation, a variant of our method we term adaptive robust imitative planning (AdaRIP). Our methods outperform current state-of-the-art approaches in the nuScenes prediction challenge, but since no benchmark evaluating OOD detection and adaption currently exists to assess control, we introduce an autonomous car novel-scene benchmark, CARNOVEL, to evaluate the robustness of driving agents to a suite of tasks with distribution shifts.


page 2

page 4

page 13

page 14

page 16


Estimating Uncertainty For Vehicle Motion Prediction on Yandex Shifts Dataset

Motion prediction of surrounding agents is an important task in context ...

Managing driving modes in automated driving systems

Current technologies are unable to produce massively deployable, fully a...

FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis

Balancing performance and safety is crucial to deploying autonomous vehi...

Learn-to-Race Challenge 2022: Benchmarking Safe Learning and Cross-domain Generalisation in Autonomous Racing

We present the results of our autonomous racing virtual challenge, based...

P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving

Motion prediction is crucial in enabling safe motion planning for autono...

On the Practicality of Deterministic Epistemic Uncertainty

A set of novel approaches for estimating epistemic uncertainty in deep n...

CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships

As machine learning models become increasingly prevalent in motion forec...

Code Repositories


A research framework for autonomous driving

view repo


A research framework for autonomous driving

view repo