We used a NABU sensor attached to a street sweeper to map the streets of Oxford, in an innovative data gathering project which will help the City Council to plan and manage its services. Read the Council's Press Release here: PRESS RELEASE 11 March 2017 Innovative new city mapping could transform council services A [...]
Ten of Oxford’s AIMS (Autonomous Intelligent Machines and Systems) CDT students joined us for our annual robotics challenge. Divided into three teams, the students had to programme a Husky robot to work its way around obstacles to reach a goal. There was some careful planning.
http://www.youtube.com/watch?v=2MSWTKBMNeE In practice, we found dense reconstructions are the most complete and highest quality (with our mobile robotics platform) when fusing data from multiple Velodyne, SICK LMS- 151, and stereo cameras using our own datasets. We are releasing such a dataset to provide a realistic mobile-robotics platform with a variety of sensors—a [...]
Classification precision and recall have been widely adopted by roboticists as canonical metrics to quantify the performance of learning algorithms. This paper advocates that for robotics applications, which often involve mission-critical decision making, good performance according to these standard metrics is desirable but insufficient to appropriately characterise system performance. We introduce and motivate the importance [...]