The performance of autonomous robots, i.e. robots that can make their own decisions and choose their own actions, is becoming increasingly impressive, but most of them are still constrained to labs, or controlled environments. In addition to this, these robots are typically only able to do intelligent things for a short period of time, before either crashing (physically or digitally) or running out of things to do. In order to go beyond these limitations, and to deliver the kind of autonomous service robots required by society, we must conquer the challenge of combining artificial intelligence and robotics to develop systems capable of long-term autonomy in everyday environments. This talk will present recent progress in this direction, focussing on the mobile robots for security and care domains developed by the EU-funded STRANDS project (http://strands-project.eu) which have so far completed over 106 days of autonomy in real service environments. In particular the presentation will cover our approach which combines probabilistic verification and machine learning to produce a planning system which controls how the robots select and execute their tasks over these extended periods of autonomy.
Nick Hawes is an Associate Professor of Engineering Science in the Oxford Robotics Institute at the University of Oxford. His research applies techniques from artificial intelligence to allow robots to perform useful tasks for, or with, humans in everyday environments (from moving goods in warehouses to supporting nursing staff in a care home). He is particularly interested in how robots can understand the world around them and how it changes over time (e.g. where objects usually appear, how people move through buildings etc.), and how robots can exploit this knowledge to perform tasks more efficiently and intelligently.
After Dr Cuayahuitl and Dr Baxter, who gave research presentations recently, we are now happy to announce a research seminar by the third colleague to join the Lincoln Centre for Autonomous Systems soon as a Senior Lecturer.
On 15/02/16, at 2pm, in room MB1020 (1st floor, Minerva Building), Dr Michael Mangan, currently still at the University of Edinburgh, will be presenting his exciting research. Everybody is invited to join in.
What can self-driving cars learn from the humble desert ant? And how are those lessons learned?
Desert ants are amongst the most impressive of the animal navigators: expertly piloting through complex environments despite possessing low-resolution eyes and tiny brains. As such they are an ideal model system for bio-roboticists that seek to understand these amazing animals, as well as those seeking novel solutions for engineering goals such as autonomous navigation. In this talk I shall firstly introduce the animal of interest (the desert ant) describing their amazing navigational capabilities. I will then briefly describe some recent examples for which our bio-robotic approach has lead to advances in understanding of the biological system and novel applications in autonomous systems (such as self-driving cars). I shall close by looking ahead to the research I shall be pursuing after joining the University of Lincoln this spring.
Frederic Siepmann, a development specialist at BMW R&D will present in our School of Computer Science research seminar series on 12/02/16 at 2pm. His talk will take place in seminar room MB1020 (1st floor Minerva Building). Frederic will share his journey from being an academic working on autonomous robots to eventually become a developer in car autonomy and assistance, providing some insights into this career path and the latest development in the field at BMW.
Title: From Autonomous Robots to Autonomous Cars – How My RoboCup Experience helped me build Software for the new BMW 7 Series
Coming from the research area of autonomous robots and now working in the automotive industry, my talk covers some of the technological challenges as well as software engineering challenges when developing highly complex and software-intensive systems.
I will give you a short overview about lessons learned from the development of autonomous robots and how the iterative development process as e.g. performed during the RoboCup@HOME tournament helped me find my way in the automotive industry.
Also, I will show some of the current technologies in driver assistance, point out similarities and differences and dare to give a short glimpse into the future.
Dr. Heriberto Cuayáhuitl, who will be joining the Lincoln School of Computer Science soon as a Senior Lecturer in L-CAS, will be presenting in our research seminar series on Fri 22/1/16, at 1pm. His talk titled “Autonomous Learning for Interactive Agents” will be held in room MB1020. This is a great opportunity for staff and students alike, to meet their colleague and lecturer to-be.
Title: Autonomous Learning for Interactive Agents
Robots that interact with humans are still confined to controlled spaces, such as lab environments, where they conduct highly pre-specified tasks in interaction with recruited and cooperative users. Some of the obstacles that restrict real world applicability (amongst others) are their heavy reliance on domain-specific pre-programming and learning tasks that arise from the real world rather than being contrived for the purpose of robot training. In this talk, I will present a research direction on autonomous learning that aims to alleviate the above problems in order to push interactive robots over the edge of wider usability. The core of my research lies in multi-task reinforcement learning that helps agents to understand and optimise their behaviour by interacting with humans and learning from feedback and examples. I will briefly present three applications of this autonomous learning framework: (1) a situated agent that learns to guide people in indoor environments using a divide-and-conquer approach, (2) a conversational robot that learns to play educational games from interacting with children, and (3) a strategic agent that learns trading negotiations using deep reinforcement learning. I will conclude by discussing directions for future research that further increase the level of autonomy of interactive agents for their application in real world scenarios.
Dr Heriberto Cuayáhuitl is a Research Fellow in the School of Mathematical and Computer Sciences at Heriot-Watt University, Edinburgh Campus. He received a PhD from the University of Edinburgh in 2009, and has been a postdoctoral researcher at the University of Bremen and the German Research Centre for Artificial Intelligence (DFKI). His research interest is in machine learning for interactive systems and robots, and he has published 60 research papers in this area. He is lead organiser of the international workshop series on Machine Learning for Interactive Systems (MLIS), and has been guest editor of the journals ACM Transactions on Interactive Interactive Systems and Elsevier Computer Speech and Language.