Science Daily December 7, 2022 Researchers at Cornell University have introduced damage intelligent soft-bodied systems via a network of self-healing light guides for dynamic sensing (SHeaLDS). Exploiting the intrinsic damage resilience of light propagation in an optical waveguide, in combination with a tough, transparent, and autonomously self-healing polyurethane urea elastomer, SHeaLDS enabled damage resilient and intelligent robots by self-healing cuts as well as detecting this damage and controlling the robot’s actions accordingly. With optimized material and structural design for hyperelastic deformation of the robot and autonomous self-healing capacity, SHeaLDS provided reliable dynamic sensing at large strains with no drift or […]
Category Archives: Robots
Using AI to train teams of robots to work together
Science Daily July 25, 2022 Multi-agent reinforcement learning (MARL) is a promising framework for solving complex tasks with many agents. However, a key challenge in MARL is defining private utility functions that ensure coordination when training decentralized agents. This challenge is especially prevalent in unstructured tasks with sparse rewards and many agents. Researchers at the University of Illinois have shown that successor features can help address this challenge by disentangling an individual agent’s impact on the global value function from that of all other agents. They used disentanglement to compactly represent private utilities that support stable training of decentralized agents […]
Robots learn household tasks by watching humans
Phys.org July 22, 2022 Researchers at Carnegie Mellon University have developed a new learning method for robots called WHIRL, short for In-the-Wild Human Imitating Robot Learning. WHIRL is an efficient algorithm for one-shot visual imitation. It can learn directly from human-interaction videos and generalize that information to new tasks, making robots well-suited to learning household chores. With WHIRL, a robot can observe those tasks and gather the video data it needs to eventually determine how to complete the job itself. The robot watched as a researcher opened the refrigerator door. It recorded his movements, the swing of the door, the […]
A robot learns to imagine itself
Science Daily July 13, 2022 Internal computational models allow robots to consider outcomes of multiple possible future actions without trying them out in physical reality. Recent progress in fully data-driven self-modeling has enabled machines to learn their own forward kinematics directly from task-agnostic interaction data. However, forward kinematic models can only predict limited aspects of the morphology, such as the position of end effectors or velocity of joints and masses. A key challenge is to model the entire morphology and kinematics without prior knowledge of what aspects of the morphology will be relevant to future tasks. Researchers at Columbia University […]
Robot overcomes uncertainty to retrieve buried objects
MIT News June 28, 2022 Researchers at MIT have built a prototype of a robotic system for RF-Visual mechanical search that leverages the mere existence of an RF-tagged item in the pile to benefit both tagged and untagged items. The two key innovations. RF-Visual Mapping, a technique that identifies and locates RF-tagged items in a pile and uses this information to construct an RF-Visual occupancy distribution map. The second innovation is RF-Visual Extraction, a policy formulated as an optimization problem that minimizes the number of actions required to extract the target object. In over 180 real-world experimental trials FuseBot outperformed […]
How many jobs do robots really replace?
MIT News May 4, 2020 In this three part series, a team of researchers in the US (MIT, Boston University) shows theoretically that robots may reduce employment and wages and that their local impacts can be estimated using variation in exposure to robots—defined from industry-level advances in robotics and local industry employment. They estimate robust negative effects of robots on employment and wages across commuting zones. According to the researchers the areas most exposed to robots after 1990 do not exhibit any differential trends before then, and robots’ impact is distinct from other capital and technologies. One more robot per […]
Technique uses magnets, light to control and reconfigure soft robots
Science Daily August 2, 2019 A team of researchers in the US (North Carolina State University, Elon University) has developed a technique that allows them to remotely control the movement of soft robots, lock them into position for as long as needed and later reconfigure the robots into new shapes. They used soft robots made of a polymer embedded with magnetic iron microparticles. Under normal conditions, the material is relatively stiff and holds its shape. However, when the material is heated using light from an LED the polymer becomes pliable the shape of the robot can be changed by remotely […]