Embodied AI 101
440 episodes — Page 3 of 9
A Stable Grasp Isn't Enough: Giving 6-DoF Grasping a Purpose
Sep 13, 202628 min
HiDream-O1-Embodied: A World Model Must Earn Its Actions
Sep 13, 202629 min
Axis's Real2Sim2Real Bet: Make the Data Prove Itself
Sep 13, 202613 min
A Rubik's Cube, Two Robot Hands, and One Category Error
Sep 12, 202630 min
UnifoLM: Predict the Interaction, Not the Whole World
Sep 12, 202633 min
Stop Making the Video Model Remember the World
Sep 11, 202632 min
Atlas Turns Phone Scans Into Robot Worlds—But Not Yet Into Physics
Sep 11, 202613 min
W²G-Net: Carrying Instance Identity from Shiny Scrap to the Gripper
Sep 10, 202633 min
When Avoidance Is Not Enough: T-CARE Gives UAV Swarms a Right-of-Way
Sep 10, 202633 min
Teaching Robots What "Better" Means
Sep 9, 202631 min
TANGO: Stop Treating a Humanoid Like a Disk on the Floor
Sep 9, 202629 min
Stop Teaching the VLA Your Camera: Robot-Centric Pointmaps as an Action-Aligned Visual Interface
Sep 8, 202631 min
One Policy, Many Bodies: Qwen-VLA's Bid to Unify Embodied AI
Sep 8, 202634 min
When the Simulator Lies About Friction: Physics as a Transfer Prior for Touch
Sep 7, 202630 min
Seeing Around Corners, Acting at the Edge: REACT as a VLA Safety Co-Pilot
Sep 7, 202633 min
RoboTok: Turning the Internet Into a Motion Search Engine for Dexterous Robots
Sep 6, 202630 min
VLAct: The VLA Backbone Is Not Just Plumbing
Sep 6, 202634 min
Two Models, One Gradient: Making World-Model RL Work for Contact-Rich Robots
Sep 5, 202633 min
GigaBrain-0.7: Scaling Robot Intelligence by Separating Acting, Thinking, and Imagining
Sep 5, 202634 min
Geometry Is the Contact Plan: Bringing Surface Reasoning Into MPC
Sep 4, 202634 min
A Swarm That Knows Its Margin: Safe Multi-Drone Transport With CBF-RL
Sep 4, 202630 min
The Optimizer Becomes a Policy: Inside RP-1's Learned Planner for Robot World Models
Sep 3, 202630 min
SAGA: Ground the Affordance, Then Learn the Motion
Sep 3, 202632 min
REMAC: Turning Robot Failures into Better Team Plans
Sep 3, 202631 min
Restore the Sensor Contract: Training-Free Robustness for Brittle VLA Policies
Sep 2, 202631 min
Before the Robot Touches Anything: Physics-Grounded Deliberation with Embodied Tree of Thoughts
Sep 2, 202631 min
MemoAct: Why Robot Memory Needs Both a Scratchpad and an Archive
Sep 1, 202634 min
When Touch Means Something: OmniVTLA and the Missing Contact Layer in Robot Foundation Models
Sep 1, 202633 min
Gaussians as State, Futures as Supervision: Inside GSP-3D
Aug 31, 202633 min
SIRModel and the Missing Geometry Layer in Vision–Language Manipulation
Aug 31, 202630 min
The Robot That Knows When to Think Twice: Inside τ0-VLA
Aug 30, 202633 min
When Should a Robot Stop Imagining? RISE and Adaptive World-Action Planning
Aug 30, 202629 min
The Crib as a Causal Laboratory: How a Playing iCub Learns "I Did That"
Aug 29, 202629 min
Feeling Around Corners: STRP Compresses Fingertip Force into Directional Touch
Aug 29, 202631 min
Give the Swarm a Pheromone Compass
Aug 28, 202629 min
When Every Weld Looks the Same: Language-Labeled Graphs for Industrial Localization
Aug 28, 202636 min
When Robot Eyes Converge: Active Stereo for Humanoid Depth
Aug 27, 202626 min
Two Clocks for Touch: How T-Rex Gives Dexterous VLAs a Reflex Arc
Aug 27, 202633 min
Let the VLM Decide, Let the Planner Drive: Inside Senna
Aug 26, 202631 min
Seeing the Nearly Invisible: Stereo Vision for Cable-Safe Agricultural UAVs
Aug 26, 202631 min
Taming the Flying Tip: Constrained MPC for Dynamic Deformable Linear Objects
Aug 25, 202632 min
Replay Is Not Reality: Embodied RL When Both Policy and Physics Shift
Aug 25, 202630 min
PPO Beyond the Simulator: What a TurtleBot3 Mapless Navigation Study Really Demonstrates
Aug 24, 202634 min
VLAs in the Wild: What 142 Papers Really Say About Generalist Robot Intelligence
Aug 23, 202634 min
VEDA and the Moment Vision Stops Being Enough
Aug 22, 202630 min
Three Ways to Buy Back Robot Data: Augment the Demonstration, Import the Semantics, Benchmark the Physics
Aug 21, 202632 min
UI-Mate: Show the Desktop Agent Once, Then Let It Replan
Aug 20, 202631 min
The Frozen VLM That Learns Anyway: Inside Spatial Memory Agent
Aug 20, 202631 min
The LLM Proposes, the Planner Disposes: VLA-SP for Verifiable Robot Manipulation
Aug 19, 202632 min
When Vision Cannot Know: MulPlanLM Lets Robot Planners Lift, Weigh, and Decide
Aug 19, 202630 min