Ken Goldberg

GaP outperforms traditional methods in variational automation tasks by leveraging directed computation graphs for real-time adaptability and improved success rates.

State-of-the-art Vision-Language Models fall short in real-world robotic applications, revealing critical gaps in their reasoning capabilities.

ASPIRE achieves a staggering 31% success rate on unseen long-horizon tasks, compared to just 4% for prior methods, highlighting its superior adaptability and efficiency.

Coding agents can now autonomously refine robotic manipulation policies to achieve a staggering 99% success rate on complex tasks, revolutionizing real-world robotics.

Playful learning strategies enable robots to acquire skills that boost performance on new tasks by over 20%, transforming how we approach robotic skill acquisition.

Tactile-reactive policies can boost robotic manipulation success rates by over 30% through innovative data collection and a new Mixture-of-Transformers architecture.

State-of-the-art surgical robotics policies can be disrupted by adversarial attacks, leading to a staggering 61% drop in task success rates.

High-quality dense rewards can elevate robotic manipulation success rates from 50% to near perfection, transforming how robots learn from their environments.

Unlock bimanual robot skills without bimanual robots: MonoDuo lets you train bimanual policies using only a single-arm robot and a human partner.