Series
IRIM Seminar Series

Permanent Link
https://hdl.handle.net/1853/70926
Series Type
Event Series
Description
Associated Organization(s)
Associated Organization(s)

Filters

1
117
Reset filters

Settings
Item Type: Publication × search.filters.applied.f.isSeriesOfPublicationTitle: IRIM Seminar Series × Type: Moving Image × End date: 2021 ×

Publication Search Results

Now showing 1 - 10 of 117
Thumbnail Image
Item

From Tool to Assistant: Towards Developing Adaptive Surgical Robots for the Operating Room

2021-11-17 , Majewicz Fey, Ann

Human-generated, preventable errors, particularly those made intra-operatively, can lead to morbidity and mortality for the patient poor training outcomes for residents, and high costs for the hospital. Surgical robotic systems could be designed to avoid these errors and improve training outcomes by interpreting, reacting to, and assisting human behavior. This talk will describe some novel datadriven methods to predict, in real-time, surgical style, expertise levels, and task difficulty; as well as present new systems that could be used to assist with surgical intervention or training in a variety of domains.

View
Thumbnail Image
Item

Understanding and Mitigating Bias in Vision Systems

2021-10-06 , Hoffman, Judy

As visual recognition models are developed across diverse applications; we need the ability to reliably deploy our systems in a variety of environments. At the same time, visual models tend to be trained and evaluated on a static set of curated and annotated data which only represents a subset of the world. In this talk, I will then cover techniques for transferring information between different visual environments and across different semantic tasks thereby enabling recognition models to generalize to previously unseen worlds, such as from simulated to real-world driving imagery. Finally, I'll touch on the pervasiveness of dataset bias and how this bias can adversely affect underrepresented subpopulations.

View
Thumbnail Image
Item

Conflict-Aware Risk-Averse and Safe Reinforcement Learning: A Meta-Cognitive Learning Framework

2021-04-14 , Modares, Hamidreza

While the success of reinforcement learning (RL) in computer games has shown impressive engineering feat, unlike the computer games, safety-critical settings such as unmanned vehicles must thrash around in the real world, which makes the entire enterprise unpredictable. Standard RL practice generally implants pre-specified performance metrics or objectives into the RL agent to encode the designers’ intention and preferences in achieving different and sometimes conflicting goals (e.g., cost efficiency, safety, speed of response, accuracy, etc.). Optimizing pre-specified performance metrics, however, cannot provide safety and performance guarantees across a vast variety of circumstances that the system might encounter in non-stationary and hostile environments. In this talk, I will discuss novel metacognitive RL algorithms to learn not only a control policy that optimizes accumulated reward values, but also what reward functions to optimize in the first place to formally assure safety with a good enough performance. I will present safe RL algorithms that adapt the focus of attention of RL algorithm to its variety of performance and safety objectives to resolve conflict and thus assure the feasibility of the reward function in a new circumstance. Moreover, model-free RL algorithms will be presented to solve the risk-averse optimal control (RAOC) problem to optimize the expected utility of outcomes while reducing the variance of cost under aleatory uncertainties (i.e., randomness). This is because, performance-critical systems must not only optimize the expected performance, but also reduce its variance to avoid performance fluctuation during RL’s course of operation. To solve the RAOC problem, I will present the three variants of RL algorithms and analyze their advantages and preferences for different situations/systems: 1) a one-shot static convex program based RL, 2) an iterative value iteration algorithm that solves a linear programming optimization at each iteration, and 3) an iterative policy iteration algorithm that solves a convex optimization at each iteration and guarantees the stability of the consecutive control policies.

View
Thumbnail Image
Item

Career Options in Robotics: Academia vs Industry

2021-02-17 , Collins, Thomas R. , Coogan, Samuel , Dellaert, Frank , Mazumdar, Anirban , Parikh, Anup , Young, Aaron

View
Thumbnail Image
Item

Tentacle-like Continuum Robots for Minimally Invasive Surgery

2021-11-03 , Chen, Yue

Intelligent animals are able to safely interact with their environments, whether those environments are hard or soft, and over a wide range of geometry. Modern robots made from serially arranged rigid links lack the dexterity, safety, and adaptability of the biological system. Continuum robot is an effective approach to enable compliant interaction with external objects and dexterous manipulation within tightly packed environments by continuously deforming its structure. In this talk, I will discuss the emerging continuum robotic technologies that can be used for minimally invasive surgery. I will talk about the concentric tube robot for intracerebral hemorrhage treatment, MRI-guided tendon driven mechanism, and the soft robots for photodynamic therapy.

View
Thumbnail Image
Item

Robotics and Warehouse Automation at Berkshire Grey

2021-09-22 , Mason, Matthew T.

This talk tells the Berkshire Grey story, from its founding in 2013 to its IPO earlier this year — the first robotics IPO since iRobot over 15 years ago. Berkshire Grey produces automated systems for e-commerce order fulfillment, parcel sortation, store replenishment, and related operations in warehouses, distribution centers, and in the back ends of stores. The talk will discuss the commercial opportunity, the technology and solutions developed by Berkshire Grey, and discuss the challenges of warehouse automation.

View
Thumbnail Image
Item

Towards Robust HRI: A Stochastic Optimization Approach

2021-03-31 , Nikolaidis, Stefanos

The growth of scale and complexity of interactions between humans and robots highlights the need for new computational methods to automatically evaluate novel algorithms and applications. Exploring the diverse scenarios of interaction between humans and robots in simulation can improve understanding of complex HRI systems and avoid potentially costly failures in real-world settings. In this talk, I propose formulating the problem of automatic scenario generation in HRI as a quality diversity problem, where the goal is not to find a single global optimum, but a diverse range of failure scenarios that explore both environments and human actions. I show how standard quality diversity algorithms can discover interesting and diverse scenarios in the shared autonomy domain. I then propose a new quality diversity algorithm, CMA-ME, that achieves significantly better performance than the state-of-the-art in benchmark domains. Finally, I discuss applications in procedural content generation and human preference learning.

View
Thumbnail Image
Item

Learning to Walk and Navigate on Legged Robots

2021-10-20 , Ha, Sehoon

Recent advances in both software and hardware opened a new horizon of robotics: artificial intelligence discovered dynamic motions in simulation and hardware became powerful enough to execute human-level stunts. However, the current state-of-the-art robots are yet far from operating in the real world due to lack of agility, robustness, efficiency, and safety. My research aims to develop intelligent legged robots that can walk and navigate robustly to work in the real world. It includes novel deep learning algorithms, automated environments, scalable learning pipelines, and sim-to-real techniques. In the long term, I plan to develop robotic companions in our home and working environments that can change how we live, work, and play.

View
Thumbnail Image
Item

Shedding Light on 3D Cameras

2021-09-08 , Gupta, Mohit

The advent (and commoditization) of low-cost 3D cameras is revolutionizing many application domains, including robotics, autonomous navigation, human computer interfaces, and recently even consumer devices such as cell-phones. Most modern 3D cameras (e.g., LiDAR) are active; they consist of a light source that emits coded light into the scene, i.e., its intensity is modulated over space, and/or time. The performance of these cameras is determined by their illumination coding functions. I will talk about our work on developing a coding theory of active 3D cameras. This theory, for the first time, abstracts several seemingly different 3D camera designs into a common, geometrically intuitive space. Based on this theory, we design novel 3D cameras that achieve up to an order of magnitude higher performance as compared to the current state-of-the art. I will also briefly talk about our work toward developing `All-Weather’ 3D cameras that can operate in extreme real-world conditions, including outdoors (e.g., a robot navigating outdoors in bright sunlight and poor weather), under multi-camera interference (e.g., multiple robots navigating in a shared space such as a warehouse), and handle optically challenging objects such as shiny metal (e.g., for an industrial robot sorting machine parts).

View
Thumbnail Image
Item

Institute for Robotics and Intelligent Machines (IRIM) Industry Day Panel - Career Options in Robotics

2021-03-17 , Burnstein, Jeff , Battles, Jon , Joppru, Mark , Balakirsky, Stephen

The robotics industry is one of the fastest growing industries in the world. The industry is rapidly changing as robotics have moved from the manufacturing floor into almost every segment of our lives. This seminar will be a panel discussion with industry leaders to discuss the career opportunities in companies and the breath of opportunities available to the students. They will discuss internship opportunities as well as full-time positions with their respective companies.

View