Archon & OpenDriveLab at RSS 2026

How can human demonstrations scale whole-body humanoid skills beyond isolated lab routines? Drawing on deployment-oriented research in humanoid systems and long-horizon robot control, the speaker will discuss how human data, execution feedback, and robust policy learning translate into contact-rich whole-body behaviors.

How can human-centric data become a principled substrate for whole-body intelligence? Drawing on sustained work in embodied intelligence, autonomous systems, and human-centric robot learning, the speaker will examine how behavior traces and demonstrations can be structured for cross-embodiment transfer. The discussion will foreground evaluation beyond isolated demos, toward robot capabilities that generalize across bodies, tasks, and environments.

What should a robot world model predict, abstract, and control to support long-horizon decision making? Drawing on a research trajectory in embodied AI systems and model-based autonomy, the speaker will connect controllable prediction with planning, imagination-based policy improvement, and evaluation. The talk will frame world models as operational interfaces between perception, memory, and physical consequence.