Science Daily October 23, 2023 Introducing anisotropic properties, and shape-change programmability to responsive hydrogels promises a host of opportunities in the development of soft robots. An international team of researchers (Canada, Germany) synthesized pH-responsive hydrogel nanocomposites with predetermined microstructural anisotropy, shape-transformation, and self-healing. They were largely composed of zwitterionic monomers and asymmetric cellulose nanocrystals. While the zwitterionic nature of the network imparted both self-healing and cytocompatibility to the hydrogel nanocomposites, the shear-induced alignment of cellulose nanocrystals rendered their anisotropic swelling and mechanical properties. They utilized a cut-and-paste approach to program reversible, and complex deformation into the hydrogels. As a proof-of-concept, […]
Tag Archives: Robots
Training robots how to learn, make decisions on the fly
Science Daily July 11, 2023 Autonomous lander missions on extraterrestrial bodies will need to sample granular material while coping with domain shift, no matter how well a sampling strategy is tuned on Earth. Researchers at the University of Illinois proposed an adaptive scooping strategy that uses deep Gaussian process method trained with meta-learning to learn on-line from very limited experience on the target terrains. Deep Meta-Learning with Controlled Deployment Gaps (CoDeGa) explicitly trained the deep kernel to predict scooping volume robustly under large domain shifts. Employed in a Bayesian Optimization sequential decision-making framework, the proposed method allowed the robot to […]
Drones navigate unseen environments with liquid neural networks
MIT News April 19, 2023 Autonomous robots can learn to perform visual navigation tasks from offline human demonstrations and generalize online and unseen scenarios within the same environment they have been trained on. It is challenging for these agents to take a step further and robustly generalize to new environments with drastic scenery changes that they have never encountered. Researchers at MIT have developed a method to create robust flight navigation agents that successfully perform vision-based fly-to-target tasks beyond their training environment under drastic distribution shifts. They designed an imitation learning framework using liquid neural networks, a brain-inspired class of […]
Robots predict human intention for faster builds
Science Daily April 5, 2023 To focus on enabling robots to proactively assist humans in assembly tasks by adapting to their preferred sequence of actions researchers at the University of Southern California proposed learning human preferences from demonstrations in a shorter, canonical task to predict user actions in the actual assembly task. The proposed system used the preference model learned from the canonical task as a prior and updates the model through interaction when predictions are inaccurate. They evaluated the proposed system in simulated assembly tasks and in a real-world human-robot assembly study and showed that both transferring the preference […]
DARPA’s Robotic In-Space Mechanic Aces Tests, on Track for Launch
DARPA November 8, 2022 DARPA is seeking to create a persistent operational dexterous robotic capability in geosynchronous Earth orbit to enable on-orbit satellite repair and upgrade, extending satellite life spans, expanding the capabilities of existing satellites, enhancing spacecraft resilience, and improving the reliability of the current U.S. space infrastructure. All component-level tests are complete on DARPA’s Robotic Servicing of Geosynchronous Satellites (RSGS) program and the on-orbit demonstration mission is on schedule for launch in 2024. Following a period of checkout and calibration activities, the program anticipates on-orbit satellite servicing activities will begin in 2025. RSGS is intended to remain in […]
How organic neuromorphic electronics can think and act
Science Daily December 13, 2021 In living organisms, sensory and motor processes are distributed, locally merged, and capable of forming dynamic sensorimotor associations. An international team of researchers (the Netherlands, Germany, USA – Stanford University, UK, Saudi Arabia, Italy) has developed a simple and efficient organic neuromorphic circuit for local sensorimotor merging and processing on a robot that is placed in a maze. While the robot is exposed to external environmental stimuli, visuomotor associations are formed on the adaptable neuromorphic circuit. With this on-chip sensorimotor integration, the robot learns to follow a path to the exit of a maze, while […]
Teaching robots to think like us
Science Daily October 26, 2021 Researchers in Japan have taught a robot to navigate through a maze by electrically stimulating a culture of brain nerve cells connected to the machine. The neurons were grown from living cells and acted as the physical reservoir for the computer to construct coherent signals. The signals are regarded as homeostatic signals, telling the robot the internal environment was being maintained within a certain range and acting as a baseline as it moved freely through the maze. Throughout trials, the robot was continually fed the homeostatic signals interrupted by the disturbance signals until it had […]
A robot that senses hidden objects
MIT News April 1, 2021 Using RF researchers at MIT have designed, implemented, and evaluated RF-Grasp, a robotic system that can grasp fully occluded objects in unknown and unstructured environments. It can identify and locate target objects through occlusions and perform efficient exploration and complex manipulation tasks in non-line-of-sight settings. It relies on an eye-in-hand camera and batteryless RFID tags attached to objects of interest. There are two main innovations: (1) an RF-visual servoing controller that uses the RFID’s location to selectively explore the environment and plan an efficient trajectory toward an occluded target, and (2) an RFvisual deep reinforcement […]
Army research enables conversational AI between soldiers, robot
EurekAlert July 27, 2020 A team of researchers in the US (US Army, University of Southern California) supported by the Army Next Generation Combat Vehicle Army Modernization Priority and the Army Priority Research Area for Autonomy has developed the Joint Understanding and Dialogue Interface (JUDI) which enables bi-directional conversational interactions between soldiers and autonomous systems through bidirectional speech and dialogue in tactical operations. The technology gives the robot the ability to ask for clarification or provide status updates as tasks are completed. The dialogue processing is based on a statistical classification method. JUDI is designed for tasks that require reasoning […]
Penn Engineering’s New Scavenger Technology Allows Robots to ‘Eat’ Metal for Energy
University of Pennsylvania, April 6, 2020 The metal-air scavenger developed by researchers at the University of Pennsylvania works like a battery by providing power by repeatedly breaking and forming a series of chemical bonds and a harvester as the power is supplied by energy in the chemical bonds in metal and air surrounding the metal-air scavenger. They showed that a range of hydrogel electrolyte compositions can be combined with air cathodes to extract 159, 87, and 179 mAh/cm2 capacities from aluminum, zinc, and steel surfaces at up to 130, 81, and 25 mW/cm2 power densities, which exceed the power density […]