SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.14911 · ICML · 2020

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

Sergey Levine, Angelos Filos, Yarin Gal, Rowan Mcallister, Panagiotis Tigas, Nicholas Rhinehart

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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, where our methods outperform all the baselines.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.14911")
get_code_for_paper("2006.14911")
have("2006.14911")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.14911.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.14911.svg)](https://syntology.ai/paper/2006.14911)

Connect an agent — have() is free.