Battery-free robots use origami to change shape in mid-air

Science Daily  September 13, 2023 Researchers at the University of Washington designed origami battery-free microfliers using bistable leaf-out structures and found that a simple change in the shape of the origami structures caused two dramatically different falling behaviors. When unfolded and flat, the microfliers exhibited a tumbling behavior that increased lateral displacement in the wind. When folded inward, their orientation was stabilized, resulting in a downward descent that was less influenced by wind. To electronically transition between these two shapes, they designed a low-power electromagnetic actuator that produced peak forces of up to 200 millinewtons within 25 milliseconds while powered […]

Discovering nanomachines within living organisms: Cytochromes P450 unleashed as living soft robots

Phys.org  August 7, 2023 An international team of researchers (Israel, India) addressed the difference between regular 3D matter and the nanomachines in ‘living matters’ (e.g., the CYP450 enzymes), which oxidize an array of essential substrate molecules. Molecular dynamics simulations revealed that, unlike 3D materials, CYP450s are 4D nanomachines, in which the fourth dimension was a sensing mechanism whereby the protein responds to an initial stimulus of substrate entrance and performs an autonomous chain of events (the catalytic cycle), which leads to substrate oxidation. They found that stimulus was the binding of a substrate molecule that eventually underwent oxidation in a […]

Allowing robots to explore on their own

Science Daily  July 21, 2023 Researchers at Carnegie Mellon University has proposed dual-resolution scheme to achieve time-efficient autonomous exploration with one or many robots using a high-resolution local map of the robot’s immediate vicinity and a low-resolution global map of the remaining areas of the environment. The high-resolution bounded local map ensures that the robots observe the entire region in detail and the computation burden is bounded. The low-resolution global map directs the robot to explore the broad space and only requires lightweight computation and low bandwidth to communicate among the robots. Their paper shows the strength of this approach […]

Researchers build bee robot that can twist

Science Daily  May 23, 2023 A team of researchers in the US (UCLA, industries, Washington State University) has developed a an insect-scale flying robot, Bee ++, driven by four independently actuated flapping wings using new method for synthesizing and implementing high-performance six-degree-of-freedom (6 -DOF) flight controllers. Each wing of the Bee ++ was installed with a preset orientation enabling reliable roll, pitch, and yaw torque generation, and a Lyapunov-based nonlinear control architecture that enabled closed-loop position and attitude regulation and tracking. The control algorithms stabilize position and attitude by independently varying the wing stroke amplitudes of the four flapping wings. […]

Researchers develop soft robot that shifts from land to sea with ease

Science Daily  March 14, 2023 A team of researcers in the USA (Carnegie Mellon University, UCLA) has developed a multimodal soft robot locomotion using highly compact and dynamic bistable soft actuators. The actuators are composed of a prestretched membrane sandwiched between two 3D printed frames with embedded shape memory alloy (SMA) coils. The actuator can swiftly transform between two oppositely curved states and generate a force through a snap-through instability that is triggered after 0.2 s of electrical activation with an electrical energy input power. The consistency and robustness of the snap-through actuator response was experimentally validated through cyclical testing. […]

Soft robot detects damage, heals itself

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 […]

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 […]