← Back to topics

Topic

Embodied Agents

Reasoning and action grounded in the physical world.

3 papers · latest 2026-04-13

Most active fields for this topic

Nastaran Darabi, Amit Ranjan Trivedi

cs.ROcs.CLcs.CV

ProGAL-VLA adds verified grounding and prospective sub-goals to VLA robots, sharply improving instruction sensitivity, ambiguity handling, and robustness under perturbation.

Yunsong Zhou, Hangxu Liu, Xuekun Jiang et al.

significant🔴 AdvancedRoboticsEmbodied Agents
cs.ROcs.AIcs.CV

SIM1 builds physics-aligned real-to-sim twins for deformable manipulation, letting purely synthetic training reach real-data parity at a fraction of collection cost and making sim-scaled robotics learning much more practical.

Jiajun Zhai, Hao Shi, Shangwei Guo et al.

cs.CVcs.MMcs.RO

E-VLA uses event cameras—normally used in robotics—to let robots see and act in near-total darkness or blur, where normal cameras fail. This enables real-world robotic systems to operate reliably in challenging environments like smoke-filled rooms or fast-moving scenes.

© 2026 A2A.pub — AI to Action. From papers to practice, daily.
Summaries are AI-assistedPrivacyTerms