Jonathan W. Hurst, Assistant Professor of Mechanical Engineering at Oregon State University, presents "Fundamentals of Walking and Running: From Animal Experiments to Robot Demonstrations" as part of the RIM Seminar Series.

Abstract
Dynamic walking and running are high-dimensional, highly dynamic, self-stable behaviors that are best implemented by a system comprised of passive elements, such as springs, and active control from sensors and computing. Animals, our best example of this dynamical system, are able to negotiate terrain that varies widely in height as well as firmness, with excellent energy economy. Robots cannot yet approach animal performance, and we contend that this lack of ability by robots is a result of lack of scientific understanding of fundamental principles of legged locomotion rather than any technological limitation.

We seek to answer these fundamental questions of how legged locomotion works, and to demonstrate discoveries by building robots and implementing principled controllers. We have found that simple controllers of the swing leg during flight can replicate observed behavior from animals, including the prioritization of injury avoidance over a steady gait in uneven terrain. Further, we have shown that a simple stance-phase force control method can explain observed biological features such as apparent leg stiffness changes or energy insertion on dissipative ground. The combination of these straightforward controllers allows a simple model to handle surprisingly variable terrain with no terrain knowledge. We currently are implementing these controllers on ATRIAS, our bipedal robot.

Tomás Lozano-Pérez, School of Engineering Professor of Teaching Excellence at MIT, presents "Integrated Task and Motion Planning in Belief Space" as part of the RIM Seminar Series.

Abstract
This talk describe an integrated strategy for planning, perception, state-estimation and action in complex mobile manipulation domains based on planning in the belief space of probability distributions over states, using hierarchical goal regression (pre-image back-chaining). We develop a vocabulary of logical expressions that describe sets of belief states, which are goals and subgoals in the planning process. We show that a relatively small set of symbolic operators can give rise to task-oriented perception in support of the manipulation goals. An implementation of this method is demonstrated in simulation and on a real PR2 robot, showing robust, flexible solution of mobile manipulation problems with multiple objects and substantial uncertainty.

Timothy Barfoot, associate professor at the University of Toronto, presents "Towards Visual Route Following for Mobile Robots…Forever!" as part of the RIM Seminar Series.

Abstract
In this talk I will describe a particular approach to visual route following for mobile robots that we have developed, called Visual Teach & Repeat (VT&R), and what I think the next steps are to make this system usable in real-world applications. We can think of VT&R as a simple form of simultaneous localization and mapping (without the loop closures) along with a path-tracking controller; the idea is to pilot a robot manually along a route once and then be able to repeat the route (in its own tracks) autonomously many, many times using only visual feedback. VT&R is useful for such applications as load delivery (mining), sample return (space exploration), and perimeter patrol (security). Despite having demonstrated this technique for over 300 km of driving on several different robots, there are still many challenges we must meet before we can say this technique is ready for real-world applications. These include (i) visual scene changes such as lighting, (ii) physical scene changes such as path obstructions, and (iii) vehicle changes such as tire wear. I’ll discuss our progress to date in addressing these issues and the next steps moving forward. There will be lots of videos.

Kristen Grauman, associate professor of computer science at UT-Austin, presents "Visual Search and Summarization" as part of the RIM Seminar Series.

Abstract
Widespread visual sensors and unprecedented connectivity have left us awash with visual data--from online photo collections, home videos, news footage, medical images, or surveillance feeds. How can we efficiently browse image and video collections based on semantically meaningful criteria? How can we bring order to the data, beyond manually defined keyword tags? We are exploring these questions in our recent work on interactive visual search and summarization.

I will first present a novel form of interactive feedback for visual search, in which a user helps pinpoint the content of interest by making visual comparisons between his envisioned target and reference images. The approach relies on a powerful mid-level representation of interpretable relative attributes to connect the user’s descriptions to the system’s internal features. Whereas traditional feedback limits input to coarse binary labels, the proposed “WhittleSearch” lets a user state precisely what about an image is relevant, leading to more rapid convergence to the desired content. Turning to issues in video browsing, I will then present our work on automatic summarization of egocentric videos. Given a long video captured with a wearable camera, our method produces a short storyboard summary. Whereas existing summarization methods define sampling-based objectives (e.g., to maximize diversity in the output summary), we take a “story-driven” approach that predicts the high-level importance of objects and their influence between subevents. We show this leads to substantially more accurate summaries, allowing a viewer to quickly understand the gist of a long video. This work is being conducted with Adriana Kovashka, Yong Jae Lee, Devi Parikh, and Lu Zheng.

Dennis Hong, associate professor of mechanical engineering at Virginia Tech, presents "From Odin to DARwIn: Robot Evolution by Intelligent Design" as part of the RIM Seminar Series.

Abstract
Most mobile robots we see today utilize wheels or treads to move around. But why don’t we see such locomotion mechanisms in nature? Or a better question we should ask is: why don’t we use locomotion mechanisms used in nature for creating robots? Animals move in various ways; crawling, walking, jumping, and undulating to name a few. Inspired by biology, when and how should we apply these concepts to create robots with higher mobility? Bioinspiration does not mean simply copying ideas from nature, but rather learning the mechanisms behind it and being inspired by them to create novel concepts and solutions that go even beyond what we see in nature.

In this talk, we present several biologically inspired mobile robots developed at RoMeLa (Robotics & Mechanisms Laboratory) between 2004 and 2012, including a unique everting robot inspired by the motility mechanisms of amoebae, a rock climbing robot that uses matching behavior, an actuated spoke wheel system for unstructured environments, a hexapod crawler with dry adhesive feet for zero gravity space applications, an autonomous wheeled vehicle that can drive itself in the urban environment, a novel three legged robot that walks more like a human, a scaffolding climbing serpentine robot that rolls up to move, and autonomous bipedal humanoid robots that can even play a game of soccer. The ability of robots created with bioinspiration can go even beyond that of animals in nature.

Raquel Urtasun of the Toyota Technological Institute at Chicago presents "Efficient Algorithms for Semantic Scene Parsing" as part of the RIM Seminar Series.

Abstract
Developing autonomous systems that are able to assist humans in everyday tasks is one of the grand challenges in modern computer science. Notable examples are personal robotics for the elderly and people with disabilities, as well as autonomous driving systems that can help decrease fatalities caused by traffic accidents. In order to perform tasks such as navigation, recognition, and manipulation of objects, these systems should be able to efficiently extract 3D knowledge of their environment. While a variety of novel sensors have been developed in the past few years, we focus on the extraction of this knowledge from visual information alone. In this talk, I'll show how Markov random fields provide a great mathematical formalism to extract this knowledge. In particular, I'll focus on a few examples; i.e., 3D reconstruction, 3D layout estimation, 2D holistic parsing and object detection, and show representations and inference strategies that allow us to achieve state-of-the-art performance as well as several orders of magnitude speed-ups.

Dan Moroni, Product Strategist at Liquid Robotics, presents on his work as part of the RIM Seminar Series.

Abstract
The presentation will go through the details of the Wave Glider and how Liquid Robotics (LRI) is working to build a platform to enable others to do ocean research without the high costs and risks of conducting ocean operations. Moroni will cover some of the challenges LRI has encountered building a persistant ocean robot and convincing some of the world's largest industries to shift how they do ocean operations. Amy Rubsamen will talk about the PacX mission and the record breaking trans-atlantic crossing.