Skip to main content
Menu

Oxford Robotics Institute | Projects - ADE

Autonomous Decision Making in Very Long Traverses (ADE)

ADE is an H2020 project funded by the European Commission within Strategic Research Cluster on Space Robotics Technologies.

The aim of ADE is to demonstrate the techniques needed to realize a planetary rover system with very long traverse capabilities (kilometres per sol) by independently taking the decisions required to progress, reduce risks and seize opportunities of data collection. The rover will be required to travel independently from a starting point (e.g. a lander) towards and end point (say a cache of sample), perform independent opportunistic science on the way and return to the lander with the acquired soil sample. The outcome sought is the demonstration of such capabilities in a terrestrial analogue of a planetary environment.

ORI Principal Investigators: Lars Kunze

ORI Team: Rhys Howard

Official Project Webpage: https://www.h2020-ade.eu

Recent Publications

  • L. Sintini and L. Kunze, “Semi-Supervised Novelty Detection in Opportunistic Science Missions using Variational Autoencoders,” in Proceedings of the British Machine Vision Conference (BMVC), 2020.
  • J. Ocón, I. Dragomir, A. Coles, A. Green, L. Kunze, R. Marc, C.J. Perez , T. Germa, V. Bissonnette, G. Scalise, and M. Foughali, "ADE: Autonomous DEcision making in very long traverses," in International Symposium on Artificial Intelligence, Robotics and Automation in Space (I-SAIRAS), 2020.
  • Ocón, J., Dragomir, I., Cordes, F., Dominguez, R., Marc, R., Bissonnette, V., Viards R, Berthet A. C., Reina G., Ugenti A., Coles A., Coles A., Green A., Howard R., and  Kunze, L. (2021). Ade: Enhancing autonomy for future planetary robotic exploration. In IAF Space Exploration Symposium 2021 at the 72nd International Astronautical Congress, IAC 2021. International Astronautical Federation, IAF.
  • R. Howard, S. Barrett and L. Kunze, "Don’t Blindly Trust Your CNN: Towards Competency-Aware Object Detection by Evaluating Novelty in Open-Ended Environments," 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi'an, China, 2021, pp. 13286-13292, doi: 10.1109/ICRA48506.2021.9562116.