Paper of the month

Visual 3D Perception for Interactive Robotic Tactile Data Acquisition by Jain, Siddarth; Corcodel, Radu; van Baar, Jeroen. IEEE International Conference on Automation Science and Engineering (CASE).

You may have seen in movies or on TV blind people recognizing people and objects by palpation. Well, these researchers from the Mitsubishi Electric Research Laboratories managed to do the same with Gen3 and tactile sensors! Not only can they redraw the shape of objects, but they can also recognize them and differentiate materials! Learn more in September's paper of the month.

An Autonomous Grape-Harvester Robot: Integrated System Architecture by Eleni Vrochidou, Konstantinos Tziridis, Alexandros Nikolaou, Theofanis Kalampokas, George A. Papakostas, Theodore P. Pachidis, Spyridon Mamalis, Stefanos Koundouras, and Vassilis G. Kaburlasos. Electronics, 10(9), 1056.

For June’s paper of the month, we are interested in applied robotics. Learn about a project by researchers from the International Hellenic University that aims to achieve Agriculture 4.0 by combining aerial units, teleoperation, and mobile manipulation for grape harvesting.

Not All Errors Are Created Equal: Exploring Human Responses to Robot Errors with Varying Severity. By Stiber, M., & Huang, C. M. (2020, October). In Companion Publication of the 2020 International Conference on Multimodal Interaction (p. 97-101).

Since robots working in close proximity with people is becoming increasingly common, these researchers from Johns Hopkins University were interested in examining the reaction time and response type of people when unexpected robot behaviors occur. Are you working on the integration of collaborative robots into safety-sensitive applications? Read about their results in April’s paper of the month.

A Motion Planning Algorithm for Redundant Manipulators Using Rapidly Exploring Randomized Trees and Artificial Potential Fields. By Anoush Sepehri and Amirreza Mirbeygi Moghaddam.

Just like robots, ideas are often better than the sum of their parts. See how these researchers from UBC and the University of Manitoba combined two well-known methods for obstacle avoidance with 7 DoF robots into a single generalized strategy that avoids the issue of both methods. The method is even showed to be transferable between different robot models!

Acoustic Collision Detection and Localization for Robot Manipulators. By Fan, X., Lee, D., Chen, Y., Prepscius, C., Isler, V., Jackel, L., ... & Lee, D. (2020). IROS.

A few months ago, we have shared a quick video presenting their work. Now that it was presented during 2020's IROS virtual event, you can read about how these researchers from Samsung AI Center - New York pulled-off near-perfect collision localization by using their new noise-proof sound-based algorithm in November's Paper of the Month!

Robot Learning and Execution of Collaborative Manipulation Plans from YouTube Cooking Videos. By Hejia Zhang and Stefanos Nikolaidis, Department of Computer Science, University of Southern California.

People often watch videos on the web to learn how to cook new recipes, assemble furniture, or repair a computer. We wish to enable robots with the very same capability. This is challenging; there is a large variation in manipulation actions and some videos even involve multiple persons, who collaborate by sharing and exchanging objects and tools.