Federated Continual Learning for Socially Aware Robotics

• URL: http://arxiv.org/abs/2201.05527v2
• Date: Mon, 10 Jul 2023 09:06:40 GMT
• Title: Federated Continual Learning for Socially Aware Robotics
• Authors: Luke Guerdan, Hatice Gunes
• Abstract summary: Social robots do not adapt their behavior to new users, and they do not provide sufficient privacy protections. We propose a decentralized learning alternative that improves the privacy and personalization of social robots. We show that decentralized learning is a viable alternative to centralized learning in a proof-of-concept Socially-Aware Navigation domain.
• Score: 4.224305864052757
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: From learning assistance to companionship, social robots promise to enhance many aspects of daily life. However, social robots have not seen widespread adoption, in part because (1) they do not adapt their behavior to new users, and (2) they do not provide sufficient privacy protections. Centralized learning, whereby robots develop skills by gathering data on a server, contributes to these limitations by preventing online learning of new experiences and requiring storage of privacy-sensitive data. In this work, we propose a decentralized learning alternative that improves the privacy and personalization of social robots. We combine two machine learning approaches, Federated Learning and Continual Learning, to capture interaction dynamics distributed physically across robots and temporally across repeated robot encounters. We define a set of criteria that should be balanced in decentralized robot learning scenarios. We also develop a new algorithm -- Elastic Transfer -- that leverages importance-based regularization to preserve relevant parameters across robots and interactions with multiple humans. We show that decentralized learning is a viable alternative to centralized learning in a proof-of-concept Socially-Aware Navigation domain, and demonstrate how Elastic Transfer improves several of the proposed criteria.

Related papers

• Towards Privacy-Aware and Personalised Assistive Robots: A User-Centred Approach [55.5769013369398]
  This research pioneers user-centric, privacy-aware technologies such as Federated Learning (FL) FL enables collaborative learning without sharing sensitive data, addressing privacy and scalability issues. This work includes developing solutions for smart wheelchair assistance, enhancing user independence and well-being.
  arXiv  Detail & Related papers  (2024-05-23T13:14:08Z)
• SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation [54.97931304488993]
  Self-improving robots that interact and improve with experience are key to the real-world deployment of robotic systems. We propose an online learning method, SELFI, that leverages online robot experience to rapidly fine-tune pre-trained control policies. We report improvements in terms of collision avoidance, as well as more socially compliant behavior, measured by a human user study.
  arXiv  Detail & Related papers  (2024-03-01T21:27:03Z)
• Robot Fine-Tuning Made Easy: Pre-Training Rewards and Policies for Autonomous Real-World Reinforcement Learning [58.3994826169858]
  We introduce RoboFuME, a reset-free fine-tuning system for robotic reinforcement learning. Our insights are to utilize offline reinforcement learning techniques to ensure efficient online fine-tuning of a pre-trained policy. Our method can incorporate data from an existing robot dataset and improve on a target task within as little as 3 hours of autonomous real-world experience.
  arXiv  Detail & Related papers  (2023-10-23T17:50:08Z)
• How Do Human Users Teach a Continual Learning Robot in Repeated Interactions? [7.193217430660011]
  We take a human-centered approach to continual learning, to understand how humans teach continual learning robots over the long term. We conducted an in-person study with 40 participants that interacted with a continual learning robot in 200 sessions. An extensive qualitative and quantitative analysis of the data collected in the study shows that there is significant variation among the teaching styles of individual users.
  arXiv  Detail & Related papers  (2023-06-30T20:29:48Z)
• SACSoN: Scalable Autonomous Control for Social Navigation [62.59274275261392]
  We develop methods for training policies for socially unobtrusive navigation. By minimizing this counterfactual perturbation, we can induce robots to behave in ways that do not alter the natural behavior of humans in the shared space. We collect a large dataset where an indoor mobile robot interacts with human bystanders.
  arXiv  Detail & Related papers  (2023-06-02T19:07:52Z)
• "No, to the Right" -- Online Language Corrections for Robotic Manipulation via Shared Autonomy [70.45420918526926]
  We present LILAC, a framework for incorporating and adapting to natural language corrections online during execution. Instead of discrete turn-taking between a human and robot, LILAC splits agency between the human and robot. We show that our corrections-aware approach obtains higher task completion rates, and is subjectively preferred by users.
  arXiv  Detail & Related papers  (2023-01-06T15:03:27Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)
• A General, Evolution-Inspired Reward Function for Social Robotics [0.0]
  We present the Social Reward Function as a mechanism to provide a real-time, dense reward function necessary for the deployment of reinforcement learning agents in social robotics. The Social Reward Function is designed to closely mimic those genetically endowed social perception capabilities of humans in an effort to provide a simple, stable and culture-agnostic reward function.
  arXiv  Detail & Related papers  (2022-02-01T18:05:31Z)
• Improving Customer Service Chatbots with Attention-based Transfer Learning [1.713291434132985]
  State-of-the-art research points towards physical robots providing customer service in person. This article explores two possibilities. Firstly, whether transfer learning can aid in the improvement of customer service chatbots between business domains.
  arXiv  Detail & Related papers  (2021-11-24T15:26:16Z)
• Continual Learning of Visual Concepts for Robots through Limited Supervision [9.89901717499058]
  My research focuses on developing robots that continually learn in dynamic unseen environments/scenarios. I develop machine learning models that produce State-of-the-results on benchmark datasets.
  arXiv  Detail & Related papers  (2021-01-26T01:26:07Z)
• From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation [3.3511723893430476]
  We argue that social navigation models can replicate, promote, and amplify societal unfairness such as discrimination and segregation. Our proposed framework consists of two components: textitlearning which incorporates social context into the learning process to account for safety and comfort, and textitrelearning to detect and correct potentially harmful outcomes before the onset.
  arXiv  Detail & Related papers  (2021-01-07T17:42:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.