Guest Jeannette Bohg is an expert in robotics who says there is a transformation happening in her field brought on by recent advances in large language models. The LLMs have a certain common sense baked in and robots are using it to plan and to reason as never before. But they still lack low-level sensorimotor control — like the fine skill it takes to turn a doorknob. New models that do for robotic control what LLMs did for language could soon make such skills a reality, Bohg tells host Russ Altman on this episode of Stanford Engineering’s The Future of Everything podcast.
Episode Reference Links:
Connect With Us:
Chapters:
(00:00:00) Introduction
Russ introduces guest Professor Jeannette Bohg, an expert in robotics from Stanford University.
(00:01:58) AI's Impact on Robotics
How AI is transforming robotics and the use of AI in high-level planning and reasoning in robotics.
(00:04:26) Challenges of Applying Language Models in Robotics
The challenges and potential of using large language models for robotic task planning and interaction between humans and robots.
(00:07:06) Data Shortages in Robotics
The scarcity of training data in robotics compared to other AI fields and its impact on development.
(00:10:43) Human-Robot Interaction and Augmentation
The potential for robots to augment human capabilities rather than replace them and different approaches to autonomy in robotics.
(00:16:41) The Future of Robotic Hardware
The current state of robotic hardware, its limitations, and what the future might hold for robotic development.
(00:19:53) The Financial and Practical Realities of Robotic Research
Cost and maintenance challenges associated with robotic research platforms, as well as practical applications of robotics in everyday life.
(00:25:11) Humanoid Robots vs. Practical Robots
The practicality and implications of designing robots that mimic human appearance and capabilities.
(00:27:55) Future Outlook and Commercial Viability
The future outlook for robotic platforms and when they might become commercially available.
(00:29:08) Conclusion
Connect With Us:
Episode Transcripts >>> The Future of Everything Website
Connect with Russ >>> Threads / Bluesky / Mastodon
Connect with School of Engineering >>>Twitter/X / Instagram / LinkedIn / Facebook
