
Teaching robots like humans: 1000 tasks in 24 hours
Imagine teaching a robot 1000 tasks in just 24 hours. Imagine teaching robots just like you teach humans. In fact, what if teaching a robot were as easy as showing it once? Humans can learn new skills almost instantly by watching, trying, or receiving a quick explanation. Robots, historically, haven’t been so lucky. Training them often requires huge datasets with real or virtual data, massive engineering effort, and weeks or months of experimentation. But that may be changing. In this episode of TechFirst, host John Koetsier talks with Edward Johns, Director of the Robot Learning Lab at Imperial College London, about a breakthrough in efficient imitation learning that allowed a robot to learn 1,000 different tasks in just 24 hours. Instead of collecting huge datasets, Johns’ team combines simulation training, clever algorithm design, and single demonstrations to dramatically speed up how robots learn. We discuss: • How robots can learn from just one demonstration • Why breaking tasks into “reach” and “interact” phases makes learning faster • The role of simulation data in robotics AI • Why robotics doesn’t have the same data advantage as large language models • The future of prompt-like robot training • Whether humanoid robots will actually learn like humans As robotics hardware rapidly improves and costs fall, breakthroughs like this could be the key to making robots truly useful in homes, factories, and everyday life. If robots are going to become real collaborators with humans, they’ll need to learn quickly ... just like we do. ⸻ Guest Edward Johns Director, Robot Learning Lab Imperial College London https://www.imperial.ac.uk ⸻ Subscribe for more conversations on AI, robotics, and the future of technology: https://techfirst.substack.com 00:00 Can robots learn as fast as humans? 00:51 Teaching a robot 1,000 tasks in 24 hours 01:08 The two-phase learning approach 02:14 Old-school robotics vs. machine learning 03:29 The robotics data bottleneck 04:47 The challenge of dynamic environments 06:04 The coming wave of robot data 06:59 Why robots must be teachable by users 08:08 Why LLM-style scaling is harder in robotics 09:42 Prompting robots with demonstrations 10:54 Probabilistic robot behavior and safety 12:20 What robots can do today 13:53 Why hardware precision still matters 16:53 When this reaches the real world 17:59 Humanoids that look human vs. learn human 18:40 The robotics boom around the world 22:34 The risk of scaling too early 23:46 Faster learning vs. more data 26:20 The next frontier in robot learning
Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.
