Speaker: Andrew Vardy, Memorial University of Newfoundland Title: Minimalist Robot Controllers for Planar Construction 4/16/24 – 2pm in WEB L102 Abstract: The Bio-Inspired Robotics Lab (BOTS) at Memorial University has been working to develop robotic swarms that can modify their environments. Potential applications range from household cleaning to clearing sea ice from shipping channels. In the planar construction task, mobile robots manipulate ambient objects into a desired shape. In this talk, I will review our recent research on planar construction and related problems. I will also provide a preview of a new approach that makes use of a minimalist robot...
Read MoreSeminar: Human-Machine and Human-Human Physical Interaction: How do we collaborate?
Talk Title: Human-Machine and Human-Human Physical Interaction: How do we collaborate? Speaker: Dr. Simone Fani 4/9/24 – 2pm in WEB L102 Talk Abstract: Human-Machine interaction is a broad term that can include multiple types of interactions between humans and machines, usually considering more “intelligent” machines. Machines, in all forms, are increasingly present in our everyday life, from computers, to technologically advanced vehicles. Although human-machine interactions are ubiquitous, commercial applications of human-robot physical interactions (HPI) remain underdeveloped because of safety concerns and the challenges of enabling seamless interactions. These challenges have prevented the development of commercial HPI devices for collaborative, assistive...
Read MoreSeminar: Cooperative Encirclement for Multi-Agent Systems
Title: Cooperative Encirclement for Multi-Agent SystemsSpeaker: Prof. Cammy Peterson 4/1/24 – 2pm in WEB L102 Abstract: Multi-agent systems (MASs) are valuable due to the advantages they offer compared to single-agent systems. MASs can increase areas of operation, provide time sensitive information, and produce high fidelity information. For example, a group of coordinating agents can provide different viewing angles on objects of interest for better target tracking and classification. This talk will discuss a decentralized method for using a MAS to cooperatively encircle moving targets. The method uses Lyapunov functions to derive control laws and is applicable to a wide...
Read MoreSeminar: General-Purpose Al for Humans, Robots, and Science
Title: General-Purpose Al for Humans, Robots, and ScienceSpeaker: Prof. Boyuan Chen from Duke 3/19/24 – 2pm in WEB L102 Abstract: Despite the accelerating progress in robotics, robots today remain relatively narrow in their capabilities. To have robots that can work seamlessly with humans, I will advocate building “generalist robots” that are good at multiple tasks, in various complex environments. My research studies how to build generalist robots by learning to model the world. I will show that current ideas on building generalist robots have produced powerful results such as robots making decisions through self-image and self-modeling, multi-agent robotic systems...
Read MoreSeminar: Using Data for Increased Realism in Haptic Modeling and Devices
Title: Using Data for Increased Realism in Haptic Modeling and DevicesSpeaker: Prof. Heather Culbertson 3/12/24 – 2pm in WEB L102 Abstract: The haptic (touch) sensations felt when interacting with the physical world create a rich and varied impression of objects and their environment. Humans can discover a significant amount of information through touch with their environment, allowing them to assess object properties and qualities, dexterously handle objects, and communicate social cues and emotions. Humans are spending significantly more time in the digital world, however, and are increasingly interacting with people and objects through a digital medium. Unfortunately, digital interactions...
Read MoreSeminar: Reinforcement learning to predict sensor signals during walking in animal models and humans
Title: Towards Human–AI SafetySpeaker: Ashley Dalrymple, Assistant Professor, Dept of Biomedical Engineering at the U 2/27/24 – 2pm in WEB L102 Abstract: Walking is how we navigate our environments, explore, and get from place-to-place. After injury to the nervous system, such as with paralysis caused by spinal cord injury or stroke, walking is often impaired. Regaining the ability to walk is of high importance to people with paralysis. Currently, clinical rehabilitation methods can only take a patient so far in terms of the recovery of function. We aim to augment the rehabilitation using electrical stimulation and/or powered orthoses. However, the extent...
Read MoreSeminar: Towards Human–AI Safety
Title: Towards Human–AI SafetySpeaker: Prof. Andrea Bajcsy at CMU 2/20/24 – 2pm in WEB L102 Abstract:As generative artificial intelligence (AI) interacts with people at an unprecedented scale—from behavior predictors that guide autonomous cars’ decision-making to language models that converse with millions of end-users—the problem of human–AI safety has exploded in interest. However, the safety consequences of an AI model’s outputs cannot be determined in an isolated context: they are tightly coupled with the responses and behavior of human users over time. My group has been formalizing this research challenge by unifying ideas from machine learning with control theory, which rigorously...
Read MoreSeminar: Smart and Autonomous Robots for Surgery
Axel Krieger, PhD Assistant Professor Department of Mechanical Engineering Johns Hopkins University Date: Feb 13 Time: 2-2:50pm Room: WEB L102 Abstract: Robotic assisted surgery (RAS) systems, incorporate highly dexterous tools, hand tremor filtering, and motion scaling to enable a minimally invasive surgical approach, reducing collateral damage and patient recovery times. However, current state-of-the-art telerobotic surgery requires a surgeon operating every motion of the robot, resulting in long procedure times and inconsistent results. The advantages of autonomous robotic functionality have been demonstrated in applications outside of medicine, such as manufacturing and aviation. A limited form of autonomous RAS with pre-planned...
Read MoreSeminar: Interactive Policy Summarization: Explaining Robot Behavior to Human Users
Date: Feb 6 Time: 2-2:50pm Room: WEB L102 Title: Interactive Policy Summarization: Explaining Robot Behavior to Human Users Abstract: We are steadily moving towards a future where humans work with robotic assistants, robotic teammates, and even robotic tutors. Yet, human users often have little knowledge of how robots work or will respond in a new situation. To ensure safe and effective use of robots, training human users regarding the robots that they work with is imperative. In pursuit of this imperative, this talk will introduce AI Teacher: an explainable AI algorithm that summarizes robot policies via demonstrations, aiming to improve...
Read MoreSeminar: Anatomics: Co-engineering Body and Machine to Improve Bionic Performance
Date: Jan 30 Time: 2-2:50pm Room: WEB L102 Title: Anatomics: Co-engineering Body and Machine to Improve Bionic Performance Abstract: Bionic systems are no longer the stuff of science fiction. Exoskeletons and prostheses restore mobility to people with physical disabilities, and augment able-bodied performance. Although a complete bionic system is made up of biological structures (“the body”) and robotic mechanisms (“the machine”), the traditional development approach focuses solely on engineering the machine. As a result, even the most advanced bionic systems are subject to fundamental limitations of the human body. In this seminar, Prof. Clites will discuss his research in the nascent...
Read More