Roadmap

Relevant Literature

League Publications

Related Articles and Survey Papers

1. G. A. Zachiotis, G. Andrikopoulos, R. Gornez, K. Nakamura, and G. Nikolakopoulos, "A Survey on the Application Trends of Home Service Robotics," in Proceedings of the IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1999-2006, 2018.
   • Discusses different application areas for service robots. Lists some relevant challenges at the end (reliability, security, ethics, acceptability)
2. M. Basiri, E. Piazza, M. Matteucci, and P. Lima, "Benchmarking Functionalities of Domestic Service Robots Through Scientific Competitions," KI-Künstliche Intelligenz, vol. 33, no. 4, pp. 357-367, 2019.
   • Presents the evaluation approach used in the European Robotics League, which is split between functionality benchmarks (controlled tests of individual functionalities, such as object detection) and task benchmarks (directly comparable to our @Home tasks)
3. I. Lee, "Service Robots: A Systematic Literature Review", Electronics, vol. 10, no. 21, e2658, 2021.
   • Discusses some important challenges for service robots in general, in particular ethics, privacy, safety and security (similar to Zachiotis et al.)
4. H. Li, S. Milani, V. Krishnamoorthy, M. Lewis, and K. Sycara, "Perceptions of Domestic Robots' Normative Behavior Across Cultures," in Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pp. 345-351, Jan. 2019.
   • Investigates the importance of a domestic robot's adaptation based on context and cultural norms
5. S. Srivastava et al., "BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments," in Conference on Robot Learning (CoRL), 2021.

Domestic Robot Functionalities

A useful domestic service robot needs to be equipped with a wide variety of functionalities and fulfill various usability criteria. This section makes an attempt at summarising such functionalities and criteria so that (a) our competition tasks can cover as many of those as possible and (b) the extent to which they are covered in the competition is proportional to their relevance for the community. For each functionality, we assign:

• a qualitative importance score between 1 and 4 according to the following scale:
  1. might be good to have, but not universally important
  2. good to have, but only somewhat important
  3. quite important, would significantly increase the robot's usefulness
  4. essential functionality
• a qualitative difficulty score on a scale between 1 and 4 based on the current state of (a) research solutions for the problem and (b) software solutions - this score is thus supposed to be regularly updated according to advances in the state of the art:
  1. generally solved research problem for which open-source software solutions are readily available
  2. generally solved problem from a research perspective, but software solutions are lacking
  3. various aspects of the problem have been addressed by the community, but various open challenges remain
  4. a generally open research problem

The score assignment is done jointly by the TC. The product of the importance and difficulty scores is used to calculate a competition relevance score, the idea being that the more important and difficult a functionality is, the more relevant it is to cover it in the competition.

The list of functionalities is compiled based on:

• relevant publications about service robots in general and domestic robots in particular - both from the league and from the broader research community
• answers to a survey that was sent to the robotics community at the end of 2021
• an initial list of functionalities that was collected by members of the TC in the context of this related issue

Domain	Functionalities	Importance (i) (1-4)	Difficulty (d) (1-4)	Relevance (r) i*d
Navigation
Manipulation
Perception
World modelling
Cognition
Human-robot interaction
Reliability and safety
Security
Ethics