Nexi, humanoid robot, Personal Robots Group, MIT Media Lab, Cambridge, Massachusetts, USA

[Airicist]

Nexi, is an M.D.S. (Mobile/Dexterous/Social) robot


Robot coming from the geniuses of MIT Media Labs Personal Robots Group (https://pr.ai/showthread.php?7697) in collaboration with Xitome Design, UMASS Amherst's Laboratory for Perceptual Robotics, and Meka Robotics. Built to the size and relative weight of a 3 year old child Nexi has a combination of mobility, dexterity, and human-centric communication and interactive abilities. It has the arm strength capability to lift up to 10 pounds and is able to move about on two wheels at a steady and even pace. And it's head and neck is able to move and gesture at human speeds to allow it to nod, shake, tilt, and orient much like that of a human neck.

[Airicist]

Article "Nexi the M.D.S. Robot from MIT (https://www.neatorama.com/2008/04/05/nexi-the-mds-robot-from-mit)"

by Ali S.
April 5, 2008

[Airicist]

https://youtu.be/aQS2zxmrrrA

Official MDS Robot Video - First Test of Expressive Ability

Uploaded on Apr 15, 2008


This video shows an initial test of the MDS (Mobile Dexterous Social) Robot designed
and built in collaboration with the MIT Media Lab's Personal Robots Group, UMASS Amherst's Laboratory for Perceptual Robotics, Xitome Design, and Meka Robotics. It illustrates the robot's expressive range of movement using scripted animations and pre-recorded speech.

[Airicist]

https://youtu.be/RQLo06V-q2M

Meet Nexi

Published on Sep 7, 2012

[Airicist]

https://youtu.be/gUqIFs9XTEw

Teleoperated Nexi

Published on Jan 16, 2015


Summary: In this video, we show Nexi, our teleoperated humanoid robot, having a conversation with a participant.

Research description: What are the nonverbal behaviors that constitute a signal related to the trustworthiness of a novel person? The psychology department at Northeastern University (NEU) identified a candidate set of nonverbal cues–face touching, arms crossed, leaning backward, and hand touching–that was hypothesized to be indicative of untrustworthy behavior. However, in order to confirm and further validate such findings, a common practice in social psychology is to employ a human actor to perform certain nonverbal cues and study their effects in a human-subjects experiment. A fundamental challenge inherent in this research design is that people regularly emit cues outside of their own awareness, which makes it difficult even for trained professional actors to express specific cues in a reliable fashion. Our strategy for meeting this challenge was to employ a social robotics platform. By utilizing a humanoid robot, we took advantage of its programmable behavior to control exactly which cues are emitted to each participant. In collaboration with the Social Emotions Lab at NEU, Johnson Graduate School of Management, and Cornell University, we found through a human-subjects experiment that the robot’s expression of the hypothesized nonverbal cues resulted in participants perceiving the robot as a less trustworthy agent.

System: We developed a system that allowed the psychologists to remotely control our complex (38 skeletal jointed) humanoid robot. Our goal was to enable them to have a natural conversation with another person through this robotic medium. The primary technical challenge was to provide expressive but precisely-timed control of the robot’s motions to non- expert users. By combining various fully-autonomous behaviors with semi-autonomous interfaces, we developed a tele-robotic interface to control the robot’s full-body motions and behaviors for a human-subjects experiment.

[Airicist]

https://youtu.be/r5xUyzFxRYo

Urban Madness Study

Published on Jan 22, 2015


The Urban Madness Study was the Personal Robots Group first multi-MDS (humanoid robot) Study in which the robots were mixed initiative (meaning they dynamically tasked themselves, even if the human didn't provide command) and the human played a leader role.

[Airicist]

https://youtu.be/NLzr3brZmFg

Training a Robot via Human Feedback

Published on Jan 22, 2015


In this MIT Media Lab "Labcast" we describe work by Postdoctoral Researcher Brad Knox to allow even technically unskilled users to train our robots. The system, called TAMER, allows users to give the robot positive and negative reinforcement, much like you would train a pet!

[Airicist]

https://youtu.be/jKAC6In2_lI

Summary of mental state manipulation research

Published on Mar 15, 2015


An implementation and evaluation of a self-as-simulator architecture for mental state manipulation through physical action. The robot models how a human’s mental states are updated through their visual perception of the world. The robot then acts on and alter the world so that the human’s perceptual and mental processes will bring about a targeted change.