Best of: How do you build a better robot? By understanding people.

The Future of Everything

A best of episode where Russ interviews computer scientist and electrical engineer, Dorsa Sadigh. They had a fantastic conversation about the work she’s doing to train robots to better understand humans, and as she shares, it turns out that one key to this work is better understanding human behavior. If you’re curious about how we’re going to make human-robot interaction work, this is a great episode to tune into again. Enjoy.

Episode Reference Links:

• Dorsa Sadigh: Website
• Dorsa Sadigh: Stanford Profile
• Ep.171 - How do you Build a Better Robot? By Understanding People. YouTube / Website (original episode)

Connect With Us:

• Episode Transcripts >>> The Future of Everything Website
• Connect with Russ >>> Threads or Twitter/X
• Connect with School of Engineering >>> Twitter/X

Chapters:

(00:00:00) Introduction

Host Russ Altman introduces guest Professor Dorsa Sadigh, a computer scientist and electrical engineer at Stanford.

(00:02:24) Bridging Robotics and Human Psychology

The journey from focusing solely on robotics to incorporating human behavioural insights to enhance robot design and functionality.

(00:05:31) Blending Cognitive Science and Robotics

The integration of cognitive science with robotics to build better computational models of human behaviour.

(00:07:35) Addressing Suboptimal Human Decision Making

Exploring human decision-making biases and their impact on robot interaction, with focus on bounded rationality and prospect theory.

(00:10:39) Robot Adaptations to Human Imperfections

How robots can adapt to human imperfections in collaborative tasks, using theories from behavioural economics.

(00:14:57) Training Robots and Humans for Better Interaction

Strategies for teaching both humans and robots to improve their interactions, including active teaching and understanding each other’s capabilities.

(00:18:41) Partner Modelling in Robotics

Insights into partner modelling in robotics, demonstrated through a scalable model in an air hockey game setup.

(00:21:54) Complex Multi-Agent Interactions

Addressing the dynamics of multi-agent systems like traffic, where autonomous and human-driven vehicles interact.

(00:24:11) Robots in Healthcare

The role of robots in healthcare, particularly in assistive technologies, and the challenges and advancements in this area.

(00:26:26) Conclusion

Connect With Us:

Episode Transcripts >>> The Future of Everything Website

Connect with Russ >>> Threads or Twitter/X

Connect with School of Engineering >>> Twitter/X