Hardware Podcasts

171. Finally! A Humanoid Robot You Can Trust

The Next Byte Podcast · 23 Apr 2024 · 23m

What this episode covers

Hosts Daniel and Forbode discuss a research project from Columbia University that aims to overcome the 'uncanny valley' in humanoid robotics by creating a robot named Emo with a highly expressive, human-like face. They detail the hardware design, which uses 26 actuators and soft silicon skin to mimic the 30 muscles of the human face, and the software training process where the robot learned expressions by watching itself in a mirror and 'binge-watching' YouTube videos of human faces. The conversation explores the concept of 'co-expression' in human interaction, the ethical implications of creating robots that are too convincing, and the potential integration of large language models like ChatGPT to provide conversational context for the robot's reactions.

Most relevant to

makers and hobbyists

Topics

Mentioned

Companies
Mouser Electronics, Figure Robotics, Wevolver
Products
Figure 01, Emo, ChatGPT
Also
Columbia University

Related episodes from other shows

Other shows on the same ground, closest first.

  • Robot Talk · 27m

    Episode 125: Chatting with robots - Gabriel Skantze

    Gabriel Skantze, Professor at KTH Royal Institute of Technology and co-founder of Furhat Robotics, discusses the design of conversational robots that use face-to-face interaction. He explains how Furhat Robotics combines animated facial projection with hardware to enable natural turn-taking and gaze coordination, addressing the uncanny valley of static screens. Skantze details commercial applications including information kiosks at Deutsche Bahn, job interview simulations, and medical training at Karolinsky Institute, while noting the challenges of using large language models for engaging, non-transactional companion interactions with the elderly.

    Robotics & autonomyAI & machine learning
    11 chapters

  • Embedded.fm · 1h 00m

    207: I Love My Robot Monkey Head (Repeat)

    Professor Ayanna Howard of Georgia Tech discusses her research on designing robots to interact with children with special needs, focusing on kinematic modeling, emotional expression, and the phenomenon of human-robot trust. She explains how robots like the Nao and Darwin Mini are used to engage users, detailing the technical challenges of creating fluid motion and reactive behaviors. Howard also addresses the 'uncanny valley,' the risks of over-trusting autonomous systems like self-driving cars, and offers advice for hobbyists and students on getting started with robotics platforms like Lego Mindstorms and ROS.

    Robotics & autonomyEmbedded firmware
    9 chapters

  • Robot Talk · 51m

    Episode 126: Why are we building humanoid robots? - Robot Talk Live

    Ben Russell, Curator of Mechanical Engineering at the Science Museum, traces the history of humanoid robots from 18th-century automatons to modern research, highlighting the psychological drive of anthropomorphism. Maryam Banitalebi Dehkordi, a Senior Lecturer at the University of Hertfordshire, discusses the use of humanoid robots in healthcare and education, noting the 'uncanny valley' effect and the importance of natural interaction for patients with dementia or autism. Petar Kormushev, Director of the Robot Intelligence Lab at Imperial College London, explains how his lab uses reinforcement learning and imitation learning on robots like 'De Niro' to enable autonomous skill acquisition in unpredictable environments.

    Robotics & autonomyAI & machine learning
    10 chapters

  • Embedded.fm · 1h 00m

    207: I Love My Robot Monkey Head

    Professor Ayanna Howard of Georgia Tech discusses her research on humanoid robots interacting with children with special needs, focusing on kinematic modeling, robot operating system (ROS), and the psychological phenomenon of human-robot trust. She explains how robots like the Nao and Darwin Mini are used to study emotional responses and behavioral nuances, while also addressing the risks of over-trusting autonomous systems like self-driving cars. The conversation covers educational robotics platforms like Lego Mindstorms and Dash & Dot, and Howard's work with EngineerGirl.org to mentor young women in engineering.

    Robotics & autonomyEmbedded firmware
    9 chapters

  • Robot Talk · 27m

    Episode 60: Making robots look human - Carl Strathearn

    Carl Strathearn, a research fellow at Edinburgh Napier University, discusses the design and application of realistic humanoid robots, specifically Euclid and Bodie, for healthcare and social care. He explains the engineering challenges of creating lifelike features, such as Euclid's lip-syncing capabilities and Bodie's gelatin-based eyes with artificial muscles, while emphasizing the importance of narrow, task-specific applications over general-purpose AI. Strathearn highlights the rigorous regulatory approval processes required for testing these robots with vulnerable populations and critiques the media's misunderstanding of current AI capabilities.

    Robotics & autonomyMechanical engineering
    7 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Next Byte Podcast. The episode itself belongs to its publisher.