IEEE Standard for Robot Task Representation

We have completed the development of a new standard on ontologies for robotics. In this case we have addressed the specification of concept related to the assignment of tasks to robots to be executed by them

The new IEEE P1872.1 Standard for Robot Task Representation is available in draft status at the IEEE Xplore repository. The purpose of the standard is to provide a robot task ontology for knowledge representation and reasoning in robotics and automation.

This standard defines an ontology that allows the representation, reasoning, and communication of task knowledge in the robotics and automation domain. The ontology includes a list of essential terms and their definitions, attributes, types, structures, properties, constraints, and relationships for planners and designers represent task knowledge allowing them to better communicate among agents in the automated system.

The standard provides a unified way of representing robot task knowledge and provides a common set of terms and definitions structured in a logical theory, allowing for unambiguous knowledge transfer among groups of human, robots, and other artificial systems. It is linked with existent robotics ontologies. Given the recent advancement in robot standards (such as ISO 15066:2016 for collaborative robots or IEEE 1872.2:2022 for autonomous robots), the proper definition and implementation of tasks and task-based robot control has become a key toward advanced human-robot interaction.

Having a shared common robot task representation will also allow for greater reuse of task knowledge among research and development efforts in the same robot domain as well as efforts in different robot domains.

Get the draft of IEEE P1872.1 Standard for Robot Task Representation from IEEE.

A new Horizon Europe project: CoreSense

We have signed a grant agreement with the EC to coordinate a new research project on intelligent robotics. The CoreSense project will develop a new hybrid cognitive architecture to make robots capable of understanding and being aware of what is going on. The project will start on October 1, 2022 will span four years (2022-2026) and joins six partners across europe in an effort to push forward the limits of robotic cognition.

Cognitive robots are augmenting their autonomy, enabling them to deployments in increasingly open-ended environments. This offers enormous possibilities for improvements in human economy and wellbeing. However, it also poses strong risks that are difficult to assess and control by humans. The trend towards increased autonomy conveys augmented problems concerning reliability, resilience, and trust for autonomous robots in open worlds. The essence of the problem can be traced to robots suffering from a lack of understanding of what is going on and a lack of awareness of their role in these situations. This is a problem that artificial intelligence approaches based on machine learning are not addressing well. Autonomous robots do not fully understand their open environments, their complex missions, their intricate realizations, and the unexpected events that affect their performance. An improvement in the capability to understand of autonomous robots is needed.

The CoreSense project tries to provide a solution to this need in the form of a AI theory of understanding, a theory of robot awareness, some enginering-grade reusable software assets to apply these theories in real robots. The project will build three demonstrations of its capability to augment resilience of drone teams, augment flexibility of manufacturing robots, and augment human alignment of social robots.

In summary, CoreSense will develop a cognitive architecture for autonomous robots based on a formal concept of understanding, supporting value-oriented situation understanding and self-awareness to improve robot flexibility, resilience and explainability.

There are six project partners:

Universidad Politécnica de Madrid – ES – Coordinator
Delft University of Technology – NL
Fraunhofer IPA – DE
Universidad Rey Juan Carlos – ES
PAL Robotics – ES
Irish Manufacturing Research – IR

Principal Investigator: Ricardo Sanz

Premio Innovatech 2020 a la tecnología inTelos

El equipo UPM ASLab + TU Delft ha obtenido el Primer Premio en el concurso UPM_innovatech 2T Challenge de 2020.

Esta es una iniciativa de desafío competitivo para investigadores, pionera en España, que busca reconocer y premiar las tecnologías más innovadoras de la Universidad Politécnica de Madrid y contribuir a su desarrollo y comercialización.

La tecnología presentada por el equipo ASLab+TUDelft, InTelos, es el resultado de años de investigación en sistemas auto-conscientes en ASLab. Esta es una tecnología que permite emplear el conocimiento de ingeniería para dotar al sistema de capacidades cognitivas de auto-percepción y control que le dotan de una mayor adaptabilidad, resiliencia y autonomía. Es una tecnología resultante del proyecto ASys.