Latest / The Robotics Podcast with Fexingo: Autonomous Systems, Industrial Robots, and Hardware
Why Robot Arms Still Cant Handle a Deflated Balloon
In this episode, Lucas and Luna explore why even the most advanced robotic grippers struggle with soft, deformable objects like a deflated balloon. They break down the physics of grasping, the limitations of current sensor technology, and how researchers are using machine learning to tackle this seemingly simple task. The discussion focuses on a 2025 study from MIT's CSAIL lab that achieved a 78% success rate with a custom gripper and reinforcement learning. The hosts also touch on the broader implications for industries like food processing and healthcare. A quick segment explains how…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.