AI Science Tracker
EN

Berkeley Artificial Intelligence Research (BAIR), University of California, Berkeley

1 discovery from 2020

Discoveries

BADGR: The Berkeley Autonomous Driving Ground Robot

Source check: Source checked. Not independent scientific confirmation.

Finding: A learned predictive model supports self-supervised robot navigation without human-labeled data. The primary v1 reports repeated indoor and off-road goal-reaching trials after about 42 hours of robot experience; results are limited to the reported platform and routes.

Technology: Self-supervised learned predictive model for goal-directed ground-robot navigation

Publication: Preprint · Test context: direct test. Catalog categories, not an evidence grade.

AI contribution
An end-to-end learned predictive model estimates action outcomes from self-supervised real-robot interaction and supports navigation.
Test and result
The primary v1 reports repeated navigation trials on indoor and off-road routes after about 42 hours of robot experience.
Limitation / still unknown
No independent replication; results are limited to the reported robot and routes.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/html/2002.05700v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary arXiv v1 full text, Methods and Results; first-version date checked..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 3/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.