AVATAR - paper in the journal Frontiers in Robotics and AI

11 February 2022 - Published by Tom Pauwels
Project partners Senne Van Baelen and Peter Slaets (Katholieke Universiteit Leuven) published an AVATAR related paper in the journal Frontiers in Robotics and AI.

The paper "Dynamic Semantic World Models and Increased Situational Awareness for Highly Automated Inland Waterway Transport" is online available.

This paper presents a set of methods to significantly enhance safe, highly-automated, close-encounter vessel manoeuvres.

The methods focus on shared automation, i.e. by combining distributed sensor and navigational data within a vessel's local environment. Such shared knowledge can be exploited by a vessel's control system, remote control centres, monitoring services, among many others. For example, "vessel A" can take advantage from the environmental and/or navigational information obtained and shared by "vessel B", or by any actor for that matter.

This paper presents a set of formalisations related to IWT that can significantly enhance safe, highly-automated, close-encounter vessel manoeuvres. With an elementary set of formal models the paper illustrates how such formalisations allow for unambiguous (data) interactions between actors on the waterway. For example, the models are used to construct shared, dynamic navigational maps that can be exploited by a mediator (human, vessel, RCC, ...) to perform, coordinate, and monitor vessel operations. In other words, vessels and/or mediators can take advantage of the distributed (shared) knowledge that is dynamically added to the map (at runtime).

See also info on AVATAR Linkedin.




AUTHOR=Van Baelen Senne, Peeters Gerben, Bruyninckx Herman, Pilozzi Paolo, Slaets Peter

TITLE=Dynamic Semantic World Models and Increased Situational Awareness for Highly Automated Inland Waterway Transport

JOURNAL=Frontiers in Robotics and AI






ABSTRACT=Automated surface vessels must integrate many tasks and motions at the same time. Moreover, vessels as well as monitoring and control services need to react to physical disturbances, to dynamically allocate software resources available within a particular environment, and to communicate with various other actors in particular navigation and traffic situations. In this work, the responsibility for the situational awareness is given to a mediator that decides how: 1) to assess the impact of the actual physical environment on the quality and performance of the ongoing task executions; 2) to make sure these tasks satisfy the system requirements; and 3) to be robust against disturbances. This paper proposes a set of semantic world models within the context of inland waterway transport, and discusses policies and methodologies to compose, use, and connect these models. Model-conform entities and relations are composed dynamically, that is, corresponding to the opportunities and challenges offered by the actual situation. The semantic world models discussed in this work are divided into two main categories: 1) the semantic description of a vessel’s own properties and relationships, called the internal world model, or body model, and 2) the semantic description of its local environment, called the external world model, or map. A range of experiments illustrate the potential of using such models to decide the reactions of the application at runtime. Furthermore, three dynamic, context-dependent, ship domains are integrated in the map as two-dimensional geometric entities around a moving vessel to increase the situational awareness of automated vessels. Their geometric representations depend on the associated relations; for example, with: 1) the motion of the vessel, 2) the actual, desired, or hypothesised tasks, 3) perception sensor information, and 4) other geometries, e.g., features from the Inland Electronic Navigational Charts. The ability to unambiguously understand the environmental context, as well as the motion or position of surrounding entities, allows for resource-efficient and straightforward control decisions. The semantic world models facilitate knowledge sharing between actors, and significantly enhance explainability of the actors’ behaviour and control decisions.