Robohub.org
Robots hallucinate humans to aid in object recognition | IEEE Spectrum
“Almost exactly a year ago, we posted about how Ashutosh Saxena’s lab at Cornell was teaching robots to use their “imaginations” to try to picture how a human would want a room organized. The research was successful, with algorithms that used hallucinated humans (which are the best sort of humans) to influence the placement of objects performing significantly better than other methods. Cool stuff indeed, and now comes the next step: labeling 3D point-clouds obtained from RGB-D sensors by leveraging contextual hallucinated people.”
See on spectrum.ieee.org
John Payne
AUAI is supported by:
Related posts :
What does it take for a robot to hold a conversation with a room, not just a person?
Umar Farooq and UK RAS STEPS
14 Aug 2026
Find out about a summer school held at Imperial College London.
Robotics roadmaps from around the world
IEEE Robotics and Automation Society (RAS)
12 Aug 2026
We embark on a tour into some of the recent and prominent robotics roadmaps from around the world.
A ‘5-in-1’ seed-sized surgical robot
Nanyang Technological University, Singapore
10 Aug 2026
Mini robot can move, cut tissue, release drugs, grip and store samples, and generate heat wirelessly
AI agents create virtual playgrounds to help robots get crucial training data
MIT News
07 Aug 2026
“SceneSmith” system uses collaborative AI agents to create realistic 3D environments of places like kitchens, hotels, and living rooms, where robots can simulate everyday chores.
Robots in society, business and culture: July 2026
IEEE Robotics and Automation Society (RAS)
06 Aug 2026
A round up of robotics stories in a new monthly series from IEEE RAS.
Simulated zebrafish and a vision-equipped robotic fish reveal how the body shapes brain circuits
Researchers look to the fish brain to create a robotic zebrafish that can autonomously swim upstream.
Researchers develop modular nanorobot
University of Basel
31 Jul 2026
A team at the University of Basel has developed a versatile nanorobot with propulsion and payload modules.
Surviving the paper deluge: a one-year study in learning from demonstration
IEEE Robotics and Automation Society (RAS)
29 Jul 2026
With the explosion of robotics research, staying current in fields like Learning from Demonstration is a monumental challenge.
