IRIM Seminar Series

Series Type
Event Series
Associated Organization(s)
Associated Organization(s)

Publication Search Results

Now showing 1 - 10 of 12
  • Item
    Robotic and Wearable Sensing Technologies for Movement Rehabilitation After Neurologic Injury
    (Georgia Institute of Technology, 2018-11-28) Reinkensmeyer, David J.
    Robotic therapy refers now to a diverse set of technologies and algorithms that can match or improve the clinical benefits achievable with conventional rehabilitation therapies after stroke and other neurologic injuries. However, the principles by which robotic therapy devices can be optimized are still not well understood. Here, I will first briefly overview the evolution of the technology and science of robot-assisted rehabilitation, including the range of control algorithms used. Then, I will describe recent experimental evidence that suggests three neuro-computational mechanisms that determine the effectiveness of robotic therapy: human slacking, Hebbian learning via proprioceptive stimulation, and mechanical modulation of reward. I will conclude by describing recent attempts to enhance the effectiveness of robotic therapy by combining it with neuro-regeneration, and by making it more accessible via “consumer stroke technology.”
  • Item
    Data-to-Decisions for Safe Autonomous Flight
    (Georgia Institute of Technology, 2018-11-07) Atkins, Ella
    Traditional sensor data can be augmented with new data sources such as roadmaps and geographical information system (GIS) Lidar/video to offer emerging unmanned aircraft systems (UAS) and urban air mobility (UAM) a new level of situational awareness. This presentation will summarize my group’s research to identify, process, and utilize GIS, map, and other real-time data sources during nominal and emergency flight planning. Specific efforts have utilized machine learning to automatically map flat rooftops as urban emergency landing sites, incorporate cell phone data into an occupancy map for risk-aware flight planning, and extend airspace geofencing into a framework capable of managing all traffic types in complex airspace and land-use environments. The presentation will end with videos illustrating recent work to experimentally validate the continuum deformation cooperative control strategy in the University of Michigan’s new M-Air netted flight facility.
  • Item
    Accelerated Optimization in the PDE Framework
    (Georgia Institute of Technology, 2018-10-24) Yezzi, Anthony
    Following the seminal work of Nesterov, accelerated optimization methods (sometimes referred to as momentum methods) have been used to powerfully boost the performance of first-order, gradient-based parameter estimation in scenarios where second-order optimization strategies are either inapplicable or impractical. Not only does accelerated gradient descent converge considerably faster than traditional gradient descent, but it performs a more robust local search of the parameter space by initially overshooting and then oscillating back as it settles into a final configuration, thereby selecting only local minimizers with an attraction basin large enough to accommodate the initial overshoot. This behavior has made accelerated search methods particularly popular within the machine learning community where stochastic variants have been proposed as well. So far, however, accelerated optimization methods have been applied to searches over finite parameter spaces. We show how a variational setting for these finite dimensional methods (recently formulated by Wibisono, Wilson, and Jordan) can be extended to the infinite dimensional setting, both in linear functional spaces as well as to the more complicated manifold of 2D curves and 3D surfaces. Moreover, we also show how extremely simple explicit discretization schemes can be used to efficiently solve the resulting class of high-dimensional optimization problems.
  • Item
    Mechanical Intelligence in Robotic Manipulation: Towards Human-Level Dexterity in Robotic and Prosthetic Hands
    (Georgia Institute of Technology, 2018-10-10) Dollar, Aaron M.
    The human hand is the pinnacle of dexterity – it has the ability to powerfully grasp a wide range of object sizes and shapes as well as delicately manipulate objects held within the fingertips. Current robotic and prosthetic systems, however, have only a fraction of that manual dexterity. My group attempts to address this gap in three main ways: examining the mechanics and design of effective hands, studying biological hand function as inspiration and performance benchmarking, and developing novel control approaches that accommodate task uncertainty. In terms of hand design, we strongly prioritize passive mechanics, including incorporating adaptive underactuated transmissions and carefully tuned compliance, and seek to maximize open-loop performance while minimizing complexity. To motivate and benchmark our efforts, we are examining human hand usage during daily activities as well as quantifying functional aspects such as precision manipulation workspaces.
  • Item
    Mathematics and Learning for Agile and Dynamic Bipedal Locomotion
    (Georgia Institute of Technology, 2018-09-26) Grizzle, Jessy W.
    Is it great fortune or a curse to do legged robotics on a university campus that has Maya Lin’s earthen sculpture, The Wave Field? Come to the talk and find out! Our work on model-based feedback control for highly dynamic locomotion in bipedal robots will be amply illustrated through images, videos, and math. The core technical portion of the presentation is a method to overcome the obstructions imposed by high-dimensional bipedal models by embedding a stable walking motion in an attractive low-dimensional surface of the system’s state space. The process begins with trajectory optimization to design an open-loop periodic walking motion of the high-dimensional model and then adding to this solution, a carefully selected set of additional open-loop trajectories of the model that steer toward the nominal motion. A drawback of trajectories is that they provide little information on how to respond to a disturbance. To address this shortcoming, supervised machine learning is used to extract a low-dimensional, state-variable realization of the open-loop trajectories. The periodic orbit is now an attractor of a low-dimensional state-variable model but is not attractive in the full-order system. We then use the special structure of mechanical models associated with bipedal robots to embed the low-dimensional model in the original model in such a manner that the desired walking motions are locally exponentially stable. When combined with robot vision, we hope this approach to control design will allow the full complexity of the Wave Field to be conquered. In any case, as Jovanotti points out, “Non c'è scommessa più persa di quella che non giocherò.” The speaker for one will keep trying!
  • Item
    Robotic Skins That Turn Inanimate Objects Into Multifunctional Robots
    (Georgia Institute of Technology, 2018-09-12) Kramer-Bottiglio, Rebecca
    Robots generally excel at specific tasks in structured environments, but lack the versatility and adaptability required to interact with and locomote within the natural world. To increase versatility in robot design, my research group is developing robotic skins that can wrap around arbitrary deformable objects to induce the desired motions and deformations. Robotic skins integrate actuation and sensing into a single conformable material, and may be applied to, removed from, and transferred between different objects to create a multitude of controllable robots with different functions to accommodate the demands of different environments. We have shown that attaching the same robotic skin to a deformable object in different ways, or to different objects, leads to unique motions. Further, we have shown that combining multiple robotic skins enables complex motions and functions. During this talk, I will demonstrate the versatility of this soft robot design approach by showing robotic skins in a wide range of applications—including manipulation tasks, locomotion, and wearables—using the same 2D robotic skins reconfigured on the surface of various 3D soft, inanimate objects.
  • Item
    Creating Robots That See
    (Georgia Institute of Technology, 2018-08-29) Corke, Peter
    This talk will define and motivate the problem of robotic vision, the challenges as well as recent progress at the Australian Centre for Robotic Vision. This includes component technologies such as novel cameras, deep learning for computer vision, transfer learning for manipulation, evaluation methodologies, and also end-to-end systems for applications such as logistics, agriculture, environmental remediation and asset inspection.
  • Item
    Deep Learning to Learn
    (Georgia Institute of Technology, 2018-08-20) Abbeel, Pieter
    Reinforcement learning and imitation learning have seen success in many domains, including autonomous helicopter flight, Atari, simulated locomotion, Go, robotic manipulation. However, sample complexity of these methods remains very high. In contrast, humans can pick up new skills far more quickly. To do so, humans might rely on a better learning algorithm or on a better prior (potentially learned from past experience), and likely on both. In this talk I will describe some recent work on meta-learning for action, where agents learn the imitation/reinforcement learning algorithms and learn the prior. This has enabled acquiring new skills from just a single demonstration or just a few trials. While designed for imitation and RL, our work is more generally applicable and also advanced the state of the art in standard few-shot classification benchmarks such as omniglot and mini-imagenet.
  • Item
    Geometry and Mechanics of Feet and Fins
    (Georgia Institute of Technology, 2018-04-11) Venkadesan, Madhusudhan
    The stiffness of propulsive appendages, such as feet and fins, is important in locomotory function. In this talk, I show that curvature-induced stiffness is the common principle underlying the stiffness of both primate feet and rayed fish fins. We use mathematical models, physical replicas, and biological experiments to arrive at this conclusion. The principle is evident in a drooping dollar bill that significantly stiffens upon slightly curling in the transverse direction.
  • Item
    Soft Miniature Mobile Robots
    (Georgia Institute of Technology, 2018-02-28) Sitti, Metin
    Soft functional materials could enable physical intelligence for small-scale (from a few millimeters down to a few micrometers overall size) mobile robots by enabling them with unique capabilities such as shape changing and programming, adaptation, and multi-functional and diverse behavior. This talk will explore our recent activities on how to design, manufacture, and control new untethered soft actuators, sensors, robots, and shape-programmable materials at the milli/microscale. First, inflated soft actuators with reversible stable deformations are proposed combining hyperelastic membranes and dielectric elastomer actuators to switch between stable deformations of sealed chambers. Next, new parallel microcracks-based ultrasensitive and highly stretchable soft strain sensors are integrated with gecko-inspired microfiber adhesives for wearable medical devices adhered on the skin. Next, new, untethered milli/microscale swimming robots inspired by spermatozoids and jellyfish are proposed using elastomeric magnetic composite materials. Static and dynamic shapes of such magnetic active soft materials are programmed using a computational design methodology. These soft robots are demonstrated to be able to have seven or more locomotion modalities (undulatory swimming, jellyfish-like swimming, water meniscus climbing, jumping, ground walking, rolling, crawling inside constrained environments, etc.) in a single robot for the first time to be able to move on complex environments, such as inside the human body. Ultrasound-guided navigation of such robots is possible towards medical functions such as local cargo/drug delivery.