School of Computing
Dr Jiacheng Tan
- Qualifications: BEng, MSc, PhD
- Role Title: Senior Lecturer
- Address: Buckingham Building, Lion Terrace, Portsmouth (UK) PO1 3HE
- Telephone: ++44 (0)23 9284 6386
- Email: firstname.lastname@example.org
- Department: School of Computing
- Faculty: Faculty of Technology
I am a Senior Lecturer at the School of Computing, University of Portsmouth. I received a BEng in Mechanical Engineering from Jilin University of Technology, Changchun, China (1983); MSc in Mechatronics from Xidian University, Xi’an, China (1989); and PhD in Computer Graphics from De Montfort University, UK (2001).
I was a Visiting Researcher in robotics in the Department of Electronic Engineering at the University of Salford, Manchester, UK (1996-1997), and a Research Fellow in artificial intelligence at the Open University, UK (2000-2002). I joined the School of Computing at the University of Portsmouth in 2002. My research interests are in the areas of computer vision, intelligent robot control, 3D computer graphics and visualisation.
Unit Coordinator and Lecturer
- Applied Computer Graphics and Vision
- 3D Computer Graphics and Animation
- Advanced Programming Concepts
My current research is in the area of computer vision, object recognition, intelligent robot control and 3D computer graphics.
I am currently working on object recognition, scene and task representation and grounding of the spatial relations in natural language for intelligent and interactive control of automatic or semi-automatic robots performing flexible tasks in unstructured environments. In particular, we are working on the issues of the knowledge-based object recognition and semantic scene representation.
We try to recognise, organise and represent the 3D objects or scenes captured by cameras or other sensors in a symbolic form that supports the representation of, and the reasoning upon, the cognitive, spatial and operational properties and knowledge of the objects. We also work on the issues of using natural language to communicate and interact with robots about the procedures of task operations and the intentions of the human operators.
Natural language analysis and knowledge engineering methods make it feasible to resolve complex operation instructions expressed in natural language into entities such as objects, actions and relations among them. Reasoning over these entities allows correct actions being generated and prediction about undetected environment and landmarks being made.
The methods and mechanisms for robots to learn operational knowledge via demonstrations and interactions are also studied.