CoRL 2026 to Host Workshop on Learning from Corrections and Interventions, CFP Open
ebiyik_ · x · 2026-09-24
The LfC Workshop at CoRL 2026 (Nov 12, 2026, Austin, Texas) is now accepting submissions.
The workshop focuses on interactive robot learning from human corrections and interventions: in real deployments, people act as supervisors who intervene only when needed, and these corrections carry rich information about task objectives, constraints, and expectations at far lower effort than continuous demonstration.
Key topics include: defining and representing correction signals (explicit vs. implicit feedback, multimodal signals, datasets and annotations); understanding human corrective behavior (trust, mental models, intervention timing, personalization); and learning rewards, policies, and constraints from noisy, imperfect corrections — including scaling to real-world robotic systems.
Researchers from robotics, ML, and human-robot interaction are invited; details and submission info are on the workshop site.
More from Embodied
- Robot Fashion Is Here: Custom Outfits for Quadrupeds After ICSR 2026 Show — heatherknight · 2026-09-24
- Same model, two placements: agentic control completes 18/20 LEGO tasks vs 6/20 for code-as-policy — paigeinsf · 2026-09-24
- After Astra: where does value go when frontier labs ship robotics brains? — mihdalal · 2026-09-24
- Robotics' GPT-3 moment may just be GPT-6 itself, argues investor — mihdalal · 2026-09-24
- Qualcomm and Prism ML Run 1-bit Bonsai VLM Locally on Snapdragon AR1 Smart Glasses — Scobleizer · 2026-09-24
- Opus 5.5 Averages Under $1 Per Robotics Trial, Scoring 1.8x Opus 5 at Half the Cost — ycombinator · 2026-09-24