- NCNR – National Center for Nuclear Robotics (EPSRC RAI Hub, robotics for extreme environments, 2017-2021)
The National Center for Nuclear Robotics (NCNR) is a multi-disciplinary EPSRC RAI (Robotics and Artificial Intelligence) Hub consisting of most leading nuclear robotics experts in the UK including Universities of Birmingham, Queen Mary, Essex, Bristol, Edinburgh, Lancaster and Lincoln. Under this project, more than 40 postdoctoral researchers and PhD researchers form a team to develop cutting edge scientific solutions to all aspects of nuclear robotics such as sensor and manipulator design, computer vision, robotic grasping and manipulation, mobile robotics, intuitive user interfaces and shared autonomy.
At the University of Lincoln, we will develop new machine learning algorithms for several crucial applications in nuclear robotics such as waste handling, cell decommissioning and site monitoring with mobile robots. Clean-up and decommissioning of nuclear waste is one of the biggest challenges for our and the next generations with enormous predicted costs (up to 200Bn£ over the next hundred years). Moreover, recent disaster situations such as Fukushima have shown the crucial importance of robotics technology for monitoring and intervention, which is missing up to date. Our team will focus on algorithms for vision guided robot grasping and manipulation, cutting, shared control and semi-autonomy, mobile robot navigation and outdoor mapping and navigation with a strong focus on machine learning and adaptation techniques. A dedicated bimanual robot arm platform is being developed, mounted a mobile platform, and to be operated using shared autonomy, tele-operation and augmented reality concepts to be developed.
- Automato (Innovate UK, 2017 – 2019)
Automato will develop an automated robotic picking system for fresh vine tomatoes. It addresses a key threat to the long-term future of the UK tomato industry arising from reduced labour availability due to likely limits on immigrant labour arising from Brexit and increased cost. Picking labour current accounts for ca. 1/3 of the production costs and could all be removed through robotic harvesting.
The tomatoes grow on vines in a reachable height of 1m to 2m. The task is to pick the ripe crop by identifying the tomatoes and the truss, grip the truss and cut it above without damaging the tomatoes. The project will develop computer vision and robot motion planning algorithms to complete the task with high accuracy and high speed. Motion planning in this scenarios is particularly challenging as the robot arm needs to navigate between the vines to pick the crop. For the successful application, it is crucial to not damage the vines.
This project has the potential to step change the tomato sector. Furthermore, the application of robotics combined with computer vision and motion planning algorithms has potential to underpin the wider deployment of RAS in multiple sectors of food production and manufacturing.
- Learn-Cars: Structured Deep Learning for Autonomous Driving (UoL, 2017-2018, Toyota Europe)
We will follow a data-driven approach to achieve human-like driving styles with human-level adaptability and personalization to the human driver/passenger. We will estimate driving controllers from collected experience and we will extract a library of different maneuvers from demonstrated data. We will use the maneuver library to plan the trajectory of the car by switching between different maneuvers. We will also use optimal control and reinforcement learning techniques to improve the single maneuvers such that the maneuvers generalize to unseen situations and possibly even outperform the human drivers. In particular, we will concentrate on learning to resolve dangerous situations such as avoiding an unexpected obstacle. An important research question for using maneuver libraries is how to switch between maneuvers. The system should produce as little number of switches as necessary to generate a smooth driving behavior. Moreover, we need to incorporate high-dimensional sensory input from the environment in the switching decision. To do so, we will investigate the use of deep learning techniques.
Contact: Gerhard Neumann (PI)
- Robo-Pick: Robots for Autonomous Mushroom Picking (UoL, 2017 – 2018, Innovate UK)
This project aims to develop a new robotic picking system to harvest fresh mushrooms reducing labour demands by ca. 66%. The work will be carried out by a consortium comprising: Littleport Mushroom Farms, a major UK mushroom supplier; ABB, a major UK-based robotic supplier; Stelram, a small specialist UK developer of robotic solutions; and the University of Lincoln, a leading research group focusing on robotic application in the food industry.
The project will integrate novel soft robotic actuators, vision systems and data analysis with autonomous robots and will deliver an end to end solution to a problem that has challenged the industry for many years. It will greatly increase the competitiveness of UK production and the outcomes are directly transferable to many sectors of the UK food and manufacturing industries.
- LearnRobotS (TUDa, 2015-2018; DFG Project, SPP Autonomous Learning)
The goal of this project is to develop a hierarchical learning system that decomposes complex motor skills into simpler elemental movements, also called movement primitives, that serve as building blocks of our movement strategy. For example, in a tennis game, such primitives can represent different tennis strokes such as a forehand stroke, a backhand stroke or a smash. As we can see, the autonomous decomposition into building blocks is inherent to many motor tasks. In this project, we want to exploit this basic structure for our learning system. To do so, our autonomous learning system has to extract the movement primitives out of observed trajectories, learn to generalize the primitives to different situations and select between, sequence or combine the movement primitives such that complex behavior can be synthesized out of the primitive building blocks. Our autonomous learning system will be applicable to learning from demonstrations as well as subsequent self improvement by reinforcement learning. Learning will take place on several layers of the hierarchy. While on the upper level, the activation policy of different primitives will be learned, the intermediate level of the hierarchy extracts meta-parameters of the primitives and autonomously learns how to adapt these parameters to the current situation. The lowest level of the hierarchy learns the control policies of the single primitives. Learning on all layers as well as the extraction of the structure of the hierarchical policy is aimed to operate with a minimal amount of dependence from a human expert. We will evaluate our autonomous learning framework on a robot table tennis platform, which will give us many insights in the hierarchical structure of complex motor tasks.
- ROMANS (TUDa, 2015-2018; EU H2020 RIA)
The RoMaNS (Robotic Manipulation for Nuclear Sort and Segregation) project will advance the state of the art in mixed autonomy for tele-manipulation, to solve a challenging and safety-critical “sort and segregate” industrial problem, driven by urgent market and societal needs. Cleaning up the past half century of nuclear waste represents the largest eenvironmental remediation project in the whole of Europe. Nuclear waste must be “sorted and segregated”, so that low-level contaminated waste is placed in low-level storage containers, rather than occupying extremely expensive and resource intensive high-level storage containers and facilities. Many older nuclear sites (>60 years in UK) contain large numbers of legacy storage containers, some of which have contents of mixed contamination levels, and sometimes unknown contents.
Several million of these legacy waste containers must now be cut open, investigated, and their contents sorted. This can only be done remotely using robots, because of the high levels of radioactive material. Current state-of-the-art practice in the industry, consists of simple tele-operation (e.g. by joystick or teach-pendant). Such an approach is not viable in the long- term, because it is prohibitively slow for processing the vast quantity of material required. The project will: 1) Develop novel hardware and software solutions for advanced bi-lateral master-slave tele-operation. 2) Develop advanced autonomy methods for highly adaptive automatic grasping and manipulation actions. 3) Combine autonomy and tele-operation methods using state-of-the-art understanding of mixed initiative planning, variable autonomy and shared control approaches.
Browse: Home / Projects