Semantic SLAM and Ontological Representation for Robot Navigation and Decision Making in Unstructured Environment

INTRODUCTION:

SLAM (Simultaneous Localisation and Mapping) allows robots to operate in an unknown environment by incrementally building a map, while simultaneously localising itself with reference to the map. Usually, such maps are represented as grid-based occupancy maps, allowing straightforward path planning. Metric maps built by sparse visual SLAM methods lack a higher-level comprehension of environment. Environment understanding is a key enabler for a robot to gain a high-level cognitive capability.

Recently, semantic SLAM has become a hugely active research area, largely motivated by the fact that semantic maps provide robots high-level environment knowledge, such as object type, spatial / temporal information, and object affordance, so that a robot can make decision with a human-like cognitive capability. In addition, such semantic maps can be integrated with ontological knowledge representation, allowing knowledge reasoning and inference to support decision making with uncertain information.

PROJECT AIMS AND METHODS:

Below are some related research interests:

•Building semantic maps is computationally expensive, especially when using deep learning for scene understanding.
•The project will develop efficient real-time algorithms for semantic mapping with limited computing resources. The project will develop algorithms of semantic SLAM with the capability of scene understanding for long-term robot navigation in feature-poor or dynamic conditions.
•Limited research has been performed on integrating domain knowledge with semantic SLAM. Such domain knowledge could be for industrial or domestic environment, and it is expected that robots could plan and work more efficiently with the capability of information reasoning.

The student will have the access to some cutting-edge facilities, and is expected to validate the research on these hardware platforms.

ELIGIBILITY

You should have obtained, or be about to obtain, a First or Upper Second Class UK Honours degree, or the equivalent qualifications gained outside the UK.

Applicants with a Lower Second Class degree will be considered if they also have a master’s degree. Applicants with a minimum Upper Second Class degree and significant relevant non-academic experience are encouraged to apply.