UTRC visit, 12 Oct 2017
Several researchers from United Technologies Research Center (UTRC) will be visiting Caltech on 12 Oct (Thu).
Schedule
- 7:45 am: arrive LAX. Drive to Pasadena
- 9:00 am: Sofie Haesaert, Annenberg Lounge
- 9:30 am: Open
- 10-11 am: seminar
- 11-11:30 am: Open (seminar followup discusssions)
- 11:30 am: Aaron Ames and Soon-Jo Chung, 266 Gates Thomas
- Noon: Lunch at the Athenaeum
- UTRC: Claudio, Julian, Sunil (?)
- Caltech: Gabor Orosz, Sofie, Jin
- 1 pm: Possible CAST lab tour (checking with Soon-Jo)
- 1:30 pm: Possible robotics lab tour (checking with Aaron)
- 2 pm: done for the day
Seminar
Autonomy and Robotics Research at United Technologies Research Center
Thursday, October 12, 10-11am
Annenberg 121
Dr. Andrzej Banaszuk – Senior Director, Systems Department
Dr. Sunil Kukreja – Associate Director, Control Systems
Dr. Claudio Pinello - Associate Director, Cyber Physical Systems
Dr. Julian Ryde - Staff Research Scientist, Cyber Physical Systems
United Technologies Research Center
East Hartford, CT and Berkeley, CA
Abstract: This presentation will give a broad overview of research at UTRC’s Systems Department, with particular focus on the areas of autonomous and intelligent systems and robotics. The research is conducted by a diverse team of researchers in dynamical systems, advanced control, applied mathematics, human factors, and robotics. Autonomous and intelligent systems research for aerial and ground robotics includes intelligent system architecture, human-machine systems, perception, collaborative motion planning with dynamic collision avoidance, manipulation, and formal verification. The presentation will conclude with a discussion of existing and future career and internship opportunities in the area of robotics. The Cyber-Physical Systems group, based in Berkeley CA, will be highlighted, including a more detailed discussion of the RenderMap technology "Exploiting the Link Between Perception and Rendering for Dense Mapping".
We introduce an approach for the real-time (2Hz) creation of a dense map and alignment of a moving robotic agent within that map by rendering using a Graphics Processing Unit (GPU). This is done by recasting the scan alignment part of the dense mapping process as a rendering task. Alignment errors are computed from rendering the scene, comparing with range data from the sensors, and minimized by an optimizer.
The proposed approach takes advantage of the advances in rendering techniques for computer graphics and GPU hardware to accelerate the algorithm. Moreover, it allows one to exploit information not used in classic dense mapping algorithms such as Iterative Closest Point (ICP) by rendering interfaces between the free space, occupied space and the unknown. The proposed approach leverages directly the rendering capabilities of the GPU, in contrast to other GPU-based approaches that deploy the GPU as a general purpose parallel computation platform.
We argue that the proposed concept is a general consequence of treating perception problems as inverse problems of rendering. Many perception problems can be recast into a form where much of the computation is replaced by render operations. This is not only efficient since rendering is fast, but also simpler to implement and will naturally benefit from future advancements in GPU speed and rendering techniques. Furthermore, this general concept can go beyond addressing perception problems and can be used for other problem domains such as path planning.
Bios
Dr. Andrzej Banaszuk is the Senior Director of the Systems Department at the United Technologies Research Center. In this role he is leading a diverse group of 140+ engineers and scientists in Connecticut, California, and Italy conducting advanced research in the areas of intelligent systems, autonomous systems, systems engineering, controls, embedded systems, cyber-physical systems, human-machine systems, dynamical systems, applied mathematics, data analytics, machine learning, computer vision, robotics, artificial intelligence, cyber-physical systems security, communication networks, and power electronics. Since joining UTRC in 1997, he has conducted research in analysis, design, and control of dynamical systems applied to jet engines, rotorcraft, electric power networks, and buildings. Since 2000 he has led collaborative multi-university research teams in the area of flow control, control of combustion instabilities, robust design of large uncertain dynamic networks, and autonomy. He is an author of 44 journal papers, 72 conference papers, and 11 patents. From 1999 to 2002, he was an Associate Editor of IEEE Transactions of Controls Systems Technology. He was appointed to serve on the Board of Governors of IEEE Control Systems Society in 2004. For his work on active and passive control of flow instabilities in jet engines he received IEEE Controls Systems Technology Award in 2007. He became an IEEE Fellow in 2011. He was elected to the Connecticut Academy of Science and Engineering in 2015. He holds Ph.D. in EE from Warsaw University of Technology and Ph.D. in Mathematics from Georgia Institute of Technology.
Dr. Julian Ryde is a Staff Scientist, Intelligent Robotic Systems, at the United Technologies Research Center in Berkeley, CA. His research focuses on perception for mobile autonomous systems particularly, localization and mapping from ranging and imaging sensors. In addition he is also investigating perceptual simulation for enhanced autonomous intelligence. Prior, he was a Research Assistant Professor in the Computer Science and Engineering Department at SUNY Buffalo where he lectured in Computational Vision and worked on perception for mobile autonomous systems. After his PhD he joined the robotics group at CSIRO’s Autonomous Systems Laboratory in Brisbane (Australia) in 2008 as a Post Doctoral Research Fellow. There he was involved in 3D perception and mapping for mining equipment such as electric rope shovels and autonomous skid steer loaders. One of his principal accomplishments was autonomous soil moving and manipulation with a skid steer loader (bobcat). His PhD was in Cooperative 3D Mapping for Multiple Mobile Robots and was from the University of Essex (UK). He has BA, MSci and MA degrees in Physics from the University of Cambridge (UK). He has authored over 35 peer-reviewed journal, conference publications and book chapters. He was awarded best conference paper at the International Conference on Robotics and Biomimetics in 2006. His research interests include mobile robot sensors, 3D mapping, multi-robot collaboration, video processing and autonomous system perception.
Dr. Claudio Pinello is the Group Leader for Cyber-Physical Systems, based in the UTRC Berkeley California office. He is responsible for the development of talent and capabilities in the areas of Model Based Design and Autonomous and Intelligent Systems. Since joining UTRC in 2009, he has performed research and engineering work in the areas of simulation for distributed embedded systems, application of formal methods to aerospace systems, reuse strategies and design space exploration. He holds a PhD in EECS from UC Berkeley. Previous research areas include automotive engine control, fault tolerant distributed systems, schedulability of distributed real time systems. He is co-inventor on one patent, received two best paper awards, the 2007 SAE Arch T. Colwell Merit Award, and a UTC award for furthering the dissemination of Model Based Design Technologies to one of our Business Units.
