HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness

ManiSkillFormer: Demonstration-Free Compositional Manipulation via Geometric Contracts and Agentic Skill Graph

Adapting robotic manipulation to new objects and tasks often requires additional demonstrations or manual engineering. Reusable manipulation skills can reduce this effort, but adapting these skills to new scenes remains challenging. We present ManiSkillFormer, a framework for demonstration-free and compositional manipu...

From acrobatics to generality: Humanoid robots at an inflection point.

This special issue examines what it takes to move humanoids beyond task-specific demonstrations toward dependable generality.

LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation

Eye Paths and Choices: A Simulated Approach to Maze Navigation Analysis

Animal-inspired AI robot learns to navigate unfamiliar terrain

What if an alien believes our robot videos?

In Hole in the Sky, an alien discovers the same problems with replicating robots that real-world roboticists have.