CoRL 2026 workshop on continually self-improving robots opens call for papers, due Sep 28

PeterStone_TX · x · 2026-09-27

Organizers including Jiaheng Hu announced a 'Continually Self-Improving Robots' workshop at CoRL 2026 (Nov 12, Austin), with papers due Sep 28 (AoE) on OpenReview, up to 8 pages, double-blind. The thesis: demonstration-driven imitation gives robots strong initial policies but won't close the long-tail reliability gap — robots must autonomously collect data, discover failures, and refine skills through interaction, an 'era of experiences'. Speakers include Abhishek Gupta (UW & Amazon FAR), Kay Ke (Physical Intelligence), Jeff Clune (UBC & Recursive), Jason Ma (Dyna), and Pete Florence (Generalist).

Original post →

More from Embodied

Embodied channel →