Contents | Science Robotics 7, 68

ONLINE COVER A Model of Oneself. Robots, like humans and animals, require self-models to be able to anticipate and plan future actions. Chen et al. developed a method that enables a robot arm to model its morphology and kinematics using an approach based on query-driven visual self-modeling. This month’s cover is a multiple-exposure image of a self-modeled robot arm touching a small red sphere while avoiding a large red cube.

Credit: Columbia Engineering

Science Robotics

Volume 7|
Issue 68|
Jul 2022

Credit: Columbia Engineering

Editorial

Science Robotics: Helping build better robots for a better future

BY
- Bradley J. Nelson
27 Jul 2022
Free

To build better machines, roboticists need to ask the right questions.

Focus

Do we really want AI to be human-like?

BY
- Tom Ziemke
- Sam Thellman
27 Jul 2022
NO ACCESS

Behavioral variability can be used to make robots more human-like, but we propose that it may be wiser to make them less so.

Abstract

Behavioral variability can be used to make robots more human-like, but we propose that it may be wiser to make them less so.

Robot therapy pets get a starring role in Lightyear and in real life

BY
- Robin R. Murphy
27 Jul 2022
NO ACCESS

Roboticists are working on real-world versions of Sox, a robot companion in Lightyear, to play therapeutic roles.

Abstract

Roboticists are working on real-world versions of Sox, a robot companion in Lightyear, to play therapeutic roles.

Research Articles

In situ bidirectional human-robot value alignment

BY
- Luyao Yuan
- Xiaofeng Gao
- Zilong Zheng
- Mark Edmonds
- Ying Nian Wu
- Federico Rossano
- Hongjing Lu
- Yixin Zhu
- Song-Chun Zhu
13 Jul 2022
NO ACCESS

An explainable artificial intelligence collaboration framework enables in situ bidirectional human-robot value alignment.

Abstract

A prerequisite for social coordination is bidirectional communication between teammates, each playing two roles simultaneously: as receptive listeners and expressive speakers. For robots working with humans in complex situations with multiple goals that ...

Fully body visual self-modeling of robot morphologies

BY
- Boyuan Chen
- Robert Kwiatkowski
- Carl Vondrick
- Hod Lipson
13 Jul 2022
NO ACCESS

A robot can learn full-body morphology via visual self-modeling to adapt to multiple motion planning and control tasks.

Abstract

Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. These “self-models” allow robots to consider outcomes of multiple possible future actions without trying them ...

3D-printed biomimetic artificial muscles using soft actuators that contract and elongate

BY
- Corrado De Pascali
- Giovanna Adele Naselli
- Stefano Palagi
- Rob B. N. Scharff
- Barbara Mazzolai
27 Jul 2022
NO ACCESS

Pneumatic actuators that contract and elongate can be scaled, tuned in force, and arranged in biomimetic configurations.

Abstract

Biomimetic machines able to integrate with natural and social environments will find ubiquitous applications, from biodiversity conservation to elderly daily care. Although artificial actuators have reached the contraction performances of muscles, the ...

Human-like behavioral variability blurs the distinction between a human and a machine in a nonverbal Turing test

BY
- F. Ciardo
- D. De Tommaso
- A. Wykowska
27 Jul 2022
NO ACCESS

Human-like temporal variability in movements is a powerful hint that humans use to ascribe humanness to robots.

Abstract

Variability is a property of biological systems, and in animals (including humans), behavioral variability is characterized by certain features, such as the range of variability and the shape of its distribution. Nevertheless, only a few studies have ...