HEAP: Human-Guided Learning and Benchmarking of Robotic Heap Sorting
Lead Research Organisation:
University of Nottingham
Department Name: School of Computer Science
Abstract
This project will provide scientific advancements for benchmarking, object recognition, manipulation and human-robot interaction. We focus on sorting a complex, unstructured heap of unknown objects --resembling nuclear waste consisting of a set of broken deformed bodies-- as an instance of an extremely complex manipulation task. The consortium aims at building an end-to-end benchmarking framework, which includes rigorous scientific methodology and experimental tools for application in realistic scenarios.
Benchmark scenarios will be developed with off-the-shelf manipulators and grippers, allowing to create an affordable setup that can be easily reproduced both physically and in simulation. We will develop benchmark scenarios with varying complexities, i.e., grasping and pushing irregular objects, grasping selected objects from the heap, identifying all object instances and sorting the objects by placing them into corresponding bins. We will provide scanned CAD models of the objects that can be used for 3D printing in order to recreate our benchmark scenarios. Benchmarks with existing grasp planners and manipulation algorithms will be implemented as baseline controllers that are easily exchangeable using ROS.
The ability of robots to fully autonomously handle dense clutters or a heap of unknown objects has been very \textit{limited} due to challenges in scene understanding, grasping, and decision making. Instead, we will rely on semi-autonomous approaches where a human operator can interact with the system (e.g. using tele-operation but not only) and giving high-level commands to complement the autonomous skill execution. The amount of autonomy of our system will be adapted to the complexity of the situation. We will also benchmark our semi-autonomous task execution
with different human operators and quantify the gap to the current SOTA in autonomous manipulation. Building on our semi-autonomous control framework, we will develop a manipulation skill learning system that learns from demonstrations and corrections of the human operator and can therefore learn complex manipulations in a data-efficient manner. To improve object recognition and segmentation in cluttered heaps, we will develop new perception algorithms and investigate interactive perception in order to improve the robot's understanding of the scene in terms of object instances, categories and properties.
Benchmark scenarios will be developed with off-the-shelf manipulators and grippers, allowing to create an affordable setup that can be easily reproduced both physically and in simulation. We will develop benchmark scenarios with varying complexities, i.e., grasping and pushing irregular objects, grasping selected objects from the heap, identifying all object instances and sorting the objects by placing them into corresponding bins. We will provide scanned CAD models of the objects that can be used for 3D printing in order to recreate our benchmark scenarios. Benchmarks with existing grasp planners and manipulation algorithms will be implemented as baseline controllers that are easily exchangeable using ROS.
The ability of robots to fully autonomously handle dense clutters or a heap of unknown objects has been very \textit{limited} due to challenges in scene understanding, grasping, and decision making. Instead, we will rely on semi-autonomous approaches where a human operator can interact with the system (e.g. using tele-operation but not only) and giving high-level commands to complement the autonomous skill execution. The amount of autonomy of our system will be adapted to the complexity of the situation. We will also benchmark our semi-autonomous task execution
with different human operators and quantify the gap to the current SOTA in autonomous manipulation. Building on our semi-autonomous control framework, we will develop a manipulation skill learning system that learns from demonstrations and corrections of the human operator and can therefore learn complex manipulations in a data-efficient manner. To improve object recognition and segmentation in cluttered heaps, we will develop new perception algorithms and investigate interactive perception in order to improve the robot's understanding of the scene in terms of object instances, categories and properties.
Planned Impact
nA
Organisations
- University of Nottingham (Lead Research Organisation)
- Bosch Group (Collaboration)
- Beko PLC R&D Centre (Collaboration)
- Italian Institute of Technology (Istituto Italiano di Tecnologia IIT) (Collaboration)
- Reckitt Benckiser (Collaboration)
- IDIAP Research Institute (Collaboration)
- Culham Science Centre (Collaboration)
- TU Wien (Collaboration)
- BAE Systems (United Kingdom) (Collaboration)
Publications
Al-Saadi Z
(2021)
A Novel Haptic Feature Set for the Classification of Interactive Motor Behaviors in Collaborative Object Transfer.
in IEEE transactions on haptics
Al-Saadi Z
(2023)
Resolving Conflicts During Human-Robot Co-Manipulation
Bauer D
(2020)
VeREFINE: Integrating Object Pose Verification With Physics-Guided Iterative Refinement
in IEEE Robotics and Automation Letters
Bottarel F
(2020)
GRASPA 1.0: GRASPA is a Robot Arm graSping Performance BenchmArk
in IEEE Robotics and Automation Letters
Chatzilygeroudis K
(2020)
A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
in IEEE Transactions on Robotics
Kaushik R
(2019)
Adaptive Prior Selection for Repertoire-Based Online Adaptation in Robotics.
in Frontiers in robotics and AI
| Title | The Thingamabobas |
| Description | 'Thingamabobas' is a playful, sensory experience where participants meet and interact with a circus troupe of performative mechanical and kinetic structures. In this animatronic and robotic circus of bizarrely wonderful machines created to inspire, delight and intrigue, including a robotic installation developed by our team in Nottingham. |
| Type Of Art | Artistic/Creative Exhibition |
| Year Produced | 2021 |
| Impact | In October 2021, to help further develop and test our learning resource for Thingamabobas Installation we delivered a series of workshops in two schools, one in Hong Kong and one in Nottingham, to explore design thinking and tinkering. We worked in collaboration with Lakeside Arts at The University of Nottingham, Djanogly Strelley Primary School UK, Hong Kong artists Agnes Pang and Zoie So and Huen King Wing School, Hong Kong. The results of our collaboration and the children's work was published in several Galleries and a panel discussion was held on 20th October at Spark 2021 British Council Online Festival. |
| URL | https://makersofimaginaryworlds.co.uk/projects/thethingambobas/ |
| Description | Multiple key findings are achieved by the project: - A reproducible object dataset and a simulation framework is disseminated publicly. In addition several datasets are created by partners, expecially TUWIEN specifically for robotic tasks. - An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning: We demonstrated findings to advance pushing operations on the heap. Pushes can serve several purposes like pushing objects in a box as in our main task, but can also be used in synergies with other manipulation tasks like grasping. - A Task-Parameterized Deep Q-Network to Push Unknown Objects in the Real World: To enable the robot to learn to push objects into a box at any position around the table, we proposed the task-parameterized multi-head deep Q-networks, which advance previous results. - Push-to-See interactive instance segmentation model: Object manipulation tasks such as sorting, search or singulation often require a visual understanding of the objects in the task space. Even if the state-of-the-art models like Mask R-CNN are highly capable in object segmentation and classification, their performance decrease when the scene is more complex and cluttered. UoN, in collaboration with KIT, has developed an interactive instance segmentation model that learns to manipulate the objects in a heap to get a better segmentation. - Probabilistic part-based scene segmentation: To cope with heaps of objects and debris, we decided to develop shape representations that are local and rotation-invariant. Assuming we can also obtain approximate models of the original objects before they got broken down in pieces, we also want that representation to be scale-invariant, as the approximate model scale might vary from the one of the real object (consider pipes of different sizes). We developed methods that create a semantic representation of the object part that enables part to object matching. - Framework for Assisted Teleoperation: The ability of robots to fully-autonomously operate in unstructured environments such as in a HEAP sorting task with previously unknown objects has been limited. Therefore, in this kind of task, it is important to leverage the human cognitive capabilities, which can be done through teleoperation. We proposed a two-layer mechanism to implement force feedback due to 1) object interactions in the slave workspace, and 2) virtual forces, e.g. those that can repel from static obstacles in the remote environment or provide task-related guidance forces. |
| Exploitation Route | The research has already started seeing interest, more funding is needed to increase TRL levels so the technologies can be transferred to real use cases. Discussions with some relevant industries (RACE, Beko, Ocado) has already started. |
| Sectors | Aerospace, Defence and Marine,Agriculture, Food and Drink,Construction,Creative Economy,Digital/Communication/Information Technologies (including Software),Environment,Healthcare,Manufacturing, including Industrial Biotechology,Culture, Heritage, Museums and Collections,Retail,Transport |
| Description | BINUS University Guest Lectures |
| Geographic Reach | Asia |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Impact | As a result of the training around 6 new students per year are being sent to UK to continue their education. |
| Description | Lecture in Connected Everything / Smart Products Beacon Summer School |
| Geographic Reach | National |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Impact | Dr Ayse Kucukyilmaz gave a lecture in the ConnectedEverything/Smart Products Beacon Summer School on 15-17 July 2020, focused on the use of collaborative robots (COBOTs) in a COVID-19 world. The summer school was delivered online and participants were funded by EPSRC. The summer school was attended by 25 PhD students / recent graduates from around the UK. Sessions related to some of the important aspects of COBOTS (safety, training, interaction, ethics). |
| URL | https://connectedeverything.ac.uk/summer-school-2020/ |
| Description | Lecture in M2L Summer School |
| Geographic Reach | Multiple continents/international |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Impact | Ayse Kucukyilmaz has given a lecture in the Mediterranean Machine Learning (M2L) summer school, which was structured around 6 days of keynotes, lectures and practical sessions. The target audience consisted primarily of Master and Doctoral students, academics, and practitioners from all around the world. The school was advertised with a public call and participants were be selected on the basis of merit and to promote diversity, mainly targeting attendees from higher education, with technical background and some understanding and practical experience of machine learning. The lecture was publicly disseminated over youtube (https://youtu.be/c7VEHpDIpmw) |
| URL | https://www.m2lschool.org/ |
| Description | Panelist for EPSRC Horizon CDT 'The PhD Experience' Panel Discussion and Q&A |
| Geographic Reach | National |
| Policy Influence Type | Influenced training of practitioners or researchers |
| Description | A*STAR Research Attachment Programme A*RAP |
| Amount | £45,000 (GBP) |
| Organisation | Agency for Science, Technology and Research (A*STAR) |
| Sector | Public |
| Country | Singapore |
| Start | 12/2021 |
| End | 12/2025 |
| Description | Next Generation Rehabilitation Technologies |
| Amount | £831,040 (GBP) |
| Funding ID | EP/W000679/1 |
| Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
| Sector | Public |
| Country | United Kingdom |
| Start | 08/2021 |
| End | 08/2024 |
| Description | Open All Senses: |
| Amount | £57,000 (GBP) |
| Funding ID | EP/T022493/1 |
| Organisation | HORIZON Digital Economy Research |
| Sector | Academic/University |
| Country | United Kingdom |
| Start | 05/2022 |
| End | 06/2023 |
| Description | SBRI UK National Robotics Proving Ground: Feasibility studies |
| Amount | £112,285 (GBP) |
| Organisation | Innovate UK |
| Sector | Public |
| Country | United Kingdom |
| Start | 02/2022 |
| End | 04/2022 |
| Title | A Novel Haptic Feature Set for the Classification of Interactive Motor Behaviors in Collaborative Object Transfer |
| Description | This repository contains raw and labelled haptic interaction data collected from human-human dyads in a joint object manipulation scenario. In our study*, we report evidence that harmonious and conflicting behavior patterns in physical human-human interaction (pHHI) can be recognized using haptic information alone without the need to track the manipulated object. In doing so, we design an experimental study where two human partners physically interact with each other to manipulate an object (see Fig. 1). *Al-saadi, Z., Sirintuna, D., Kucukyilmaz, A., Basdogan, C., 2021, "A Novel Haptic Feature Set for the Classification of Interactive Motor Behaviors in Collaborative Object Transfer", IEEE Transactions on Haptics, DOI: 10.1109/TOH.2020.3034244 |
| Type Of Material | Database/Collection of data |
| Year Produced | 2021 |
| Provided To Others? | Yes |
| Impact | The dataset is openly disseminated by the research community and has started to be investigated by external researchers. |
| URL | https://rml.ku.edu.tr/repository/koc-university-human-human-interaction-behaviour-pattern-recognitio... |
| Title | HEAP object grasping dataset |
| Description | Object dataset for grasping evaluation and training, which contains procedurally generated objects of controllable difficulty. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2021 |
| Provided To Others? | Yes |
| Impact | The dataset is shared with the HEAP community and was used in 3 different papers cross institutions. |
| URL | https://github.com/heap-chist-era/object_grasping_dataset |
| Title | Human-Human Interaction Behaviour Dataset for Pattern Recognition |
| Description | This repository contains labelled haptic interaction data collected from Human-Human dyads in a joint object manipulation scenario. We conducted an experimental study to generate data that can be used to identify human-human haptic interaction patterns and learn models for capturing salient characteristics of dyadic interactions. |
| Type Of Material | Database/Collection of data |
| Year Produced | 2015 |
| Provided To Others? | Yes |
| Impact | Data shared with community and was used in at least 5 papers cross-institutionally. |
| URL | https://github.com/HCRLabRepo/HHIBehaviorDataset |
| Description | BAE Systems |
| Organisation | BAE Systems |
| Country | United Kingdom |
| Sector | Academic/University |
| PI Contribution | Discussed robotics and shared control mechanisms to be applied on BAE applications, including remote healthcare delivery. |
| Collaborator Contribution | BAE has offered use of facilities and supported 3 EPSRC grant proposals with support letters. |
| Impact | Project ideas |
| Start Year | 2022 |
| Description | Beko Plc |
| Organisation | Beko PLC R&D Centre |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We created a partnership with with Beko to start in the form of one joint PhD studentship to be part funded by the company. The company will benefit from our know how provided through outcomes of different projects to advance their domestic products. We have started discussions on long term autonomy, robotic failure management, and shared control in the device operations. |
| Collaborator Contribution | Beko has agreed to share their use cases. Beko will part-fund an international PhD studentship starting in 2023/2024, with agreement to be negotiated afterwards. |
| Impact | NA. |
| Start Year | 2022 |
| Description | Bosch |
| Organisation | Bosch Group |
| Country | Global |
| Sector | Private |
| PI Contribution | We defined the benchmarking scenarios that Bosch (BCAI in Renningen) is also using to evaluate their algorithms. |
| Collaborator Contribution | Bosch is also interested in the Benchmarking scenarios and actively contributing the the project with a small research group. |
| Impact | - Addional Benchmarks for heap manipulation |
| Start Year | 2019 |
| Description | CHAPTER - Cognitive HumAn in the looP TEleopeRations |
| Organisation | Culham Science Centre |
| Department | Remote Applications in Challenging Environments (RACE) |
| Country | United Kingdom |
| Sector | Public |
| PI Contribution | TAS Hub pump priming award |
| Collaborator Contribution | With increasingly autonomous robotics taking on lots of the physical workload for people, current HRI research looks to how collaborative robots might adapt with an awareness of the mental workload being experienced by users. Research continues to develop on two fronts: making estimates of user state from mixed observable data, and understanding how different options for autonomy affect the efforts of users. This demonstrator will achieve two things: 1) embodying recent research findings into a reusable demonstrator for subsequent studies of autonomous cobots, and 2) testing the application of a new neuroergonomics machine learning framework. |
| Impact | This is a collaboration between human factors, neuroscience, psychology and computer science. |
| Start Year | 2022 |
| Description | DOMINOES: aDaptive human-rObot teaMINg fOr rEmote taskS |
| Organisation | Culham Science Centre |
| Department | Remote Applications in Challenging Environments (RACE) |
| Country | United Kingdom |
| Sector | Public |
| PI Contribution | Connected Everything Feasibility Study |
| Collaborator Contribution | This project focuses on the analysis of human workload to design effective human-robot teaming for remote teleoperation, where the robotic system may also be equipped with adaptive behaviours (e.g. smoothly following a given trajectory based on human intentions). A manufacturing scenario is designed in collaboration with industrial partner RACE,to create test cases to investigate different sources of workload (physical and cognitive). We evaluate the feasibility of using physiological workload indicators in robotic teleoperation. |
| Impact | This is a multidisciplinary project involving experts in psychology, human factors, neuroscience and computer science. |
| Start Year | 2023 |
| Description | HEAP Consortium |
| Organisation | Idiap Research Institute |
| Country | Switzerland |
| Sector | Charity/Non Profit |
| PI Contribution | The Heap project consists of an international consortium funded by chist-Era. Our project focuses on benchmarking robotic manipulation algorithms for sorting a heap of unknown objects. The contributions from the University of Lincoln were to develop the specifications of the robot benchmark platform as well as the simulation framework for benchmarking heap manipulations. We are actively collaborating with IDIAP on learning pushing and grasping strategies and with TU Vienna on active scene segmentation. |
| Collaborator Contribution | Other partners are implementing benchmark scenarios and benchmarking state of the art algorithms. Moreover, new algorithms for grasping, scene segmentation and pushing are being developed by our partners. |
| Impact | - Definition and implementation of benchmarking scenarios for heap manipulation |
| Start Year | 2019 |
| Description | HEAP Consortium |
| Organisation | Italian Institute of Technology (Istituto Italiano di Tecnologia IIT) |
| Country | Italy |
| Sector | Academic/University |
| PI Contribution | The Heap project consists of an international consortium funded by chist-Era. Our project focuses on benchmarking robotic manipulation algorithms for sorting a heap of unknown objects. The contributions from the University of Lincoln were to develop the specifications of the robot benchmark platform as well as the simulation framework for benchmarking heap manipulations. We are actively collaborating with IDIAP on learning pushing and grasping strategies and with TU Vienna on active scene segmentation. |
| Collaborator Contribution | Other partners are implementing benchmark scenarios and benchmarking state of the art algorithms. Moreover, new algorithms for grasping, scene segmentation and pushing are being developed by our partners. |
| Impact | - Definition and implementation of benchmarking scenarios for heap manipulation |
| Start Year | 2019 |
| Description | HEAP Consortium |
| Organisation | Vienna University of Technology |
| Country | Austria |
| Sector | Academic/University |
| PI Contribution | The Heap project consists of an international consortium funded by chist-Era. Our project focuses on benchmarking robotic manipulation algorithms for sorting a heap of unknown objects. The contributions from the University of Lincoln were to develop the specifications of the robot benchmark platform as well as the simulation framework for benchmarking heap manipulations. We are actively collaborating with IDIAP on learning pushing and grasping strategies and with TU Vienna on active scene segmentation. |
| Collaborator Contribution | Other partners are implementing benchmark scenarios and benchmarking state of the art algorithms. Moreover, new algorithms for grasping, scene segmentation and pushing are being developed by our partners. |
| Impact | - Definition and implementation of benchmarking scenarios for heap manipulation |
| Start Year | 2019 |
| Description | Reckitt |
| Organisation | Reckitt Benckiser |
| Country | United Kingdom |
| Sector | Private |
| PI Contribution | We discussed our work in long term autonomy with Reckitt and will develop an inspection use case with a mobile quadruped robot. |
| Collaborator Contribution | Reckitt has agreed to part fund an international PhD studentship to work on the project and will share the facilities and the use case. |
| Impact | NA |
| Start Year | 2022 |
| Description | UKAEA RACE |
| Organisation | Culham Science Centre |
| Department | Remote Applications in Challenging Environments (RACE) |
| Country | United Kingdom |
| Sector | Public |
| PI Contribution | We have started our partnership with RACE through the teleoperation use cases developed primarily for the HEAP project. The collaboration extended to agile and feasilibility studies funded by the TAS-HUB and ConnectedEverything. The company benefits from our expertise in teleoperation interfaces and shared control. |
| Collaborator Contribution | RACE has share their use cases on JET and the MASCOT system. They supported a CDT student, who started his studies in 2021/2022 through access to facilities and will part fund an international PhD studentship starting in 2023/2024. We are in the process of writing research grants |
| Impact | Bid funded by TAS-Hub Agile Programme Bid funded by Connected Everything Feasibility Studies 1 Workshop and 1 IEEE conference paper The collaboration is multidisciplinary, with experts contributing from psychology, neuroscience, human factors, computer science as well as RACE engineering. |
| Start Year | 2021 |
| Title | HEAP Simulation Framework |
| Description | Maintained by the ALR team at KIT, this Python written framework offers a robotic simulation environment, which defines a Franka Panda robot model with few objects. Two physics engine interfaces (PyBullet and Mujoco) are available in this simulation, which fulfill the requirements of different tasks in scientific research and teaching usage. |
| Type Of Technology | Software |
| Year Produced | 2020 |
| Open Source License? | Yes |
| Impact | The Simulation Framework is used by the HEAP consortium and has been used by researchers in Universities of Bristol and Birmingham, as well as Bosch. |
| Title | Push-to-See: Learning Non-Prehensile Manipulation to Enhance Instance Segmentation via Deep Q-Learning |
| Description | This is the main repository of our Push-to-See model for the ICRA 2022 paper: Serhan, B., Pandya, H., Kucukyilmaz, A., & Neumann, G. (2022, May). Push-to-see: learning non-prehensile manipulation to enhance instance segmentation via deep q-learning. In 2022 International Conference on Robotics and Automation (ICRA) (pp. 1513-1519). IEEE. https://ieeexplore.ieee.org/document/9811645 Trained model weights Mask-RG (trained on Inria objects for 40 epochs): Push-DQN (trained for 41k episodes): |
| Type Of Technology | Software |
| Year Produced | 2020 |
| Open Source License? | Yes |
| Impact | Shared with community for cross-use. Recent paper, haven't received benchmarks yet. |
| URL | https://ieeexplore.ieee.org/document/9811645 |
| Description | BAE Systems strategic planning workshop |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Industry/Business |
| Results and Impact | Discussions with BAE systems started. Research collaboration links are established with BAE providing support letters to 3 bids currently being evaluated. |
| Year(s) Of Engagement Activity | 2022 |
| Description | ISCF cross-hub initiative 'Digital Twins and Digital Tissue for Robotic Inspections, Maintenance and Repair' |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Our researcher Dr Mithun Poozhiyil joined the cross-hub initiative 'Digital Twins and Digital Tissue for Robotic Inspections, Maintenance and Repair' managed by four UKRI research Hubs (FAIRSPACE, NCNR, ORCA and RAIN) within the ISCF's 'Robots for a Safer World' scheme. He attended meetings and presented live demos of our long-distance master-slave teleoperation concept using haptic and cobot slave systems. The meetings are ongoing, fostering collaborations and raising awareness of our research. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://orcahub.org/articles/iscf-robots-for-a-safer-world-cross-hub-activities |
| Description | Invited Talk at AgriFoRwArdS Seminar Series |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | A research seminar was given at the EPSRC AgriFoRwArdS CDT Seminar Series. A mix of undergraduate and postgraduate students and research staff attended the Zoom seminar, which focused on shared control and roles for human-robot teamwork. The talk is followed by a discussion session, where participants displayed great interest in the subject area. The talk is streamed on youtube. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://www.youtube.com/channel/UCJPcGfoLEpHH37TdbdwZUCA |
| Description | Invited Talk at IRLab Seminar Series |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | A research seminar was given at the IRLab of University of Birmingham. A mix of undergraduate and postgraduate students, full time researchers and senior research staff attended the Zoom seminar, which focused on human-robot teamwork. The talk is followed by a discussion session, where students displayed great interest in the subject area. A youtube link is shared |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://www.youtube.com/watch?v=7fOkN7oG2Ec&feature=youtu.be |
| Description | Invited speaker at the Pint of Science public engagement event |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Public/other audiences |
| Results and Impact | Pint of Science is a grassroots non-profit organisation that has grown astronomically over the few years since two people decided to share their research in the pub. The aim of the event is to to provide a space for researchers and members of the public alike to come together, be curious, and chat about research in a relaxed environment outside of mysterious laboratories or daunting dark lecture theatres. The event was attended by the public in a casual environment, where our work on robotic wheelchairs and robotics in general is discussed and disseminated. |
| Year(s) Of Engagement Activity | 2023 |
| URL | https://pintofscience.co.uk/about/ |
| Description | Invited talk at CHI-WORK Online conversations: How Human-Robot Interaction is changing the way work is done |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | An online conversation with the HCI community in the CHIWork series. A mix of professionals attended a panel organised over Zoom, which focused on how robotics will change the future of work. The talk is followed by a discussion session, where participants displayed great interest in the subject area. The talk is streamed on youtube. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://www.chiwork.org/uncategorized/chiwork-conversation-with-ayse-kucukyilmaz-hosted-by-max-wilso... |
| Description | Invited talk at ICVS ORMR workshop |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Invited speaker at International Conference on Vision Systems, gave a talk on benchmarking activities as part of the HEAP project. |
| Year(s) Of Engagement Activity | 2021 |
| URL | https://sites.google.com/view/ormr-icvs2021 |
| Description | National Nuclear User Facility for Hot Robotics (NNUF-HR) Town Hall Meeting |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Academic and industry stakeholders attended the meeting. The day included presentations from NNUF regional nodes, where participants discussed ideas ideas and recommendations for equipment and capabilities that the facility will offer. |
| Year(s) Of Engagement Activity | 2019 |
| URL | https://southwestnuclearhub.ac.uk/event/national-nuclear-user-facility-hot-robotics-town-hall-meetin... |
| Description | Panelist at Bogazici University Robotics and Automation Society (RAS) BROCUP |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | Regional |
| Primary Audience | Postgraduate students |
| Results and Impact | Invited panelist for a seminar organised along with student competitions. Discussions were around use of robots in different domains, how they would affect social life and what are exciting research directions for up and coming researchers. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Presentation and Live Demo at UKRI ISCF Cross Hub webinars |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | We attended the ISCF cross-hub webinar organised by the EPSRC ORCA Hub. Within the Teleoperation / Manipulation session, we presented our work on long distance master-slave teleoperation over Internet, and showcased a live demo between University of Nottingham and University of Lincoln. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://orcahub.org/engagement/iscf-robots-for-a-safer-world/iscf-cross-hub-webinars |
| Description | Presentation at RACE |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | 10 researchers from UKAEA attended the talk, which sparked discussion on potential venues of collaboration and the use of teleoperation for nuclear handling withing the RACE premises. The company reported interest in the subject area and future collaboration plans are drawn. |
| Year(s) Of Engagement Activity | 2019 |
| Description | Presentation at UKRI RAIN Hub HRI Worhshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Professional Practitioners |
| Results and Impact | Ayse Kucukyilmaz gave a talk at the RAIN Hub Human-Robot Interaction (HRI) Workshop on 28-29 September. Dr Kucukyilmaz was attended the panel at the end of the event, where the outcomes of the sessions were summarised and feedback from attendants and industry stakeholders were sought. |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://www.eventbrite.co.uk/e/human-robot-interaction-for-nuclear-workshop-tickets-115138644786# |
| Description | Reckitt collaboration meeting |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Professional Practitioners |
| Results and Impact | Day visit to Reckitt where discussions around future collaboration was made. The company has agreed to fund 2 PhD studentships to start integration of robotic technologies in their factory. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Research Seminar at Department of Engineering La Salle - Universitat Ramon Llull |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Undergraduate students |
| Results and Impact | A research seminar was given at the Department of Engineering in La Salle - Universitat Ramon Llull. A mix of undergraduate and postgraduate students attended the Zoom seminar, which focused on variable autonomy and learning from humans in human-robot interaction. The talk is followed by a discussion session, where students displayed great interest in the subject area. |
| Year(s) Of Engagement Activity | 2021 |
| Description | Science in the Park Exhibition |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Public/other audiences |
| Results and Impact | Science in the Park was organised to provide a range of exciting family friendly activities at Wollaton Park on Saturday 5th March. A robotic stand was created for the day. A total of 856 visitors joined the event on the day. Interactions with children and young people of all ages increased interest in robotic technologies, including teleoperation and social and touch-based experiences. |
| Year(s) Of Engagement Activity | 2022 |
| URL | https://wollatonhall.org.uk/science-in-the-park-2022/ |
| Description | Speaker at CHIST-ERA seminar |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Periodic CHIST-ERA seminar, which is programme-wide. Communicated project progress to research council representatives and researchers. |
| Year(s) Of Engagement Activity | 2021,2022 |
| Description | Talk in CRNS Webinar Series |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Postgraduate students |
| Results and Impact | Ayse Kucukyilmaz gave a seminar at the University of Plymouth Centre for Robotics and Neural Systems CRNS@Webinar series of virtual research workshops. The seminars mainly targeted the University of Plymouth postgraduate students and academic staff from different research groups, but was open top public. Researchers from national and international academic and research institutions gave talks on advanced topics in Artificial Intelligence, Machine Learning and Robotics. The webinar was streamed l |
| Year(s) Of Engagement Activity | 2020 |
| URL | https://www.plymouth.ac.uk/research/robotics-neural-systems/crnswebinar-archive |
| Description | UoN NTU Collaboration Workshop |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | Local |
| Primary Audience | Other audiences |
| Results and Impact | Researchers from Nottingham Trent University visited the research organisation. Presentations were made around research outputs and new discussions for collaborations have started. |
| Year(s) Of Engagement Activity | 2021 |