Continual Learning for Affective Robotics: Why, What and How?

Date

2020-01-01

Author

Churamani, Nikhil
Kalkan, Sinan
Gunes, Hatice

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

153
views

0
downloads

Creating and sustaining closed-loop dynamic and social interactions with humans require robots to continually adapt towards their users' behaviours, their affective states and moods while keeping them engaged in the task they are performing. Analysing, understanding and appropriately responding to human nonverbal behaviour and affective states are the central objectives of affective robotics research. Conventional machine learning approaches do not scale well to the dynamic nature of such real-world interactions as they require samples from stationary data distributions. The real-world is not stationary, it changes continuously. In such contexts, the training data and learning objectives may also change rapidly. Continual Learning (CL), by design, is able to address this very problem by learning incrementally. In this paper, we argue that CL is an essential paradigm for creating fully adaptive affective robots (why). To support this argument, we first provide an introduction to CL approaches and what they can offer for various dynamic (interactive) situations (what). We then formulate guidelines for the affective robotics community on how to utilise CL for perception and behaviour learning with adaptation (how). For each case, we reformulate the problem as a CL problem and outline a corresponding CL-based solution. We conclude the paper by highlighting the potential challenges to be faced and by providing specific recommendations on how to utilise CL for affective robotics.

URI

https://hdl.handle.net/11511/88511

DOI

https://doi.org/10.1109/ro-man47096.2020.9223564

Collections

Department of Computer Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Perpetual Robot Swarm: Long-Term Autonomy of Mobile Robots Using On-the-fly Inductive Charging Arvin, Farshad; Watson, Simon; Turgut, Ali Emre; Espinosa, Jose; Krajnik, Tomas; Lennox, Barry (2018-12-01) Swarm robotics studies the intelligent collective behaviour emerging from long-term interactions of large number of simple robots. However, maintaining a large number of robots operational for long time periods requires significant battery capacity, which is an issue for small robots. Therefore, re-charging systems such as automated battery-swapping stations have been implemented. These systems require that the robots interrupt, albeit shortly, their activity, which influences the swarm behaviour. In this p...
Lifelong learning and personalization in long-term human-robot interaction (LEAP-HRI) Irfan, Bahar; Ramachandran, Aditi; Spaulding, Samuel; Kalkan, Sinan; Parisi, German I.; Gunes, Hatice (2021-03-08) While most of the research in Human-Robot Interaction (HRI) focuses on short-term interactions, long-term interactions require bolder developments and a substantial amount of resources, especially if the robots are deployed in the wild. Robots need to incrementally learn new concepts or abilities in a lifelong fashion to adapt their behaviors within new situations and personalize their interactions with users to maintain their interest and engagement. The "Lifelong Learning and Personalization in Long-Term ...
Simple and complex behavior learning using behavior hidden Markov Model and CobART Seyhan, Seyit Sabri; Alpaslan, Ferda Nur; Department of Computer Engineering (2013) In this thesis, behavior learning and generation models are proposed for simple and complex behaviors of robots using unsupervised learning methods. Simple behaviors are modeled by simple-behavior learning model (SBLM) and complex behaviors are modeled by complex-behavior learning model (CBLM) which uses previously learned simple or complex behaviors. Both models have common phases named behavior categorization, behavior modeling, and behavior generation. Sensory data are categorized using correlation based...
Swarm robotics: From sources of inspiration to domains of application Şahin, Erol (2005-01-01) Swarm robotics is a novel approach to the coordination of large numbers of relatively simple robots which takes its inspiration from social insects. This paper proposes a definition to this newly emerging approach by 1) describing the desirable properties of swarm robotic systems, as observed in the system-level functioning of social insects, 2) proposing a definition for the term swarm robotics, and putting forward a set of criteria that can be used to distinguish swarm robotics research from other multi-r...
Swarm robotics: From sources of inspiration to domains of application Şahin, Erol (Springer Verlag; 2005-09-01) Swarm robotics is a novel approach to the coordination of large numbers of relatively simple robots which takes its inspiration from social insects. This paper proposes a definition to this newly emerging approach by 1) describing the desirable properties of swarm robotic systems, as observed in the system-level functioning of social insects, 2) proposing a definition for the term swarm robotics, and putting forward a set of criteria that can be used to distinguish swarm robotics research from other multi-r...

Citation Formats

N. Churamani, S. Kalkan, and H. Gunes, “Continual Learning for Affective Robotics: Why, What and How?,” 2020, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/88511.