Abstract
Nowadays, autonomous service robots are becoming an important topic in robotic research. Differently from typical industrial scenarios, with highly controlled environments, service robots must show an additional robustness to task perturbations and changes in the characteristics of their sensory feedback. In this paper, a robot is taught to perform two different cleaning tasks over a table, using a learning from demonstration paradigm. However, differently from other approaches, a convolutional neural network is used to generalize the demonstrations to different, not yet seen dirt or stain patterns on the same table using only visual feedback, and to perform cleaning movements accordingly. Robustness to robot posture and illumination changes is achieved using data augmentation techniques and camera images transformation. This robustness allows the transfer of knowledge regarding execution of cleaning tasks between heterogeneous robots operating in different environmental settings. To demonstrate the viability of the proposed approach, a network trained in Lisbon to perform cleaning tasks, using the iCub robot, is successfully employed by the DoRo robot in Peccioli, Italy.
Highlights
IntroductionMans, are becoming part of our past
We extend the works presented in [18] and [4] using a Convolutional neural networks (CNNs)/TP-Gaussian Mixture Models (GMM) system, trained on a dataset collected on the iCub robot in Lisbon-Portugal, to control the Domestic Robot (DoRo) in Peccioli-Italy while cleaning a table
(66 original samples) the performance of the neural network and of the TPGMM correlating it with the amount of training examples used and data augmentation strategies and ii) real-world experiments testing the learned architecture on a different robotic platform - the DoRo robot
Summary
Mans, are becoming part of our past Nowadays, robots share their working environment with us, needing the ability to handle unexpected situations, to interact with humans, and to not interfering with co-workers actions (both humans and robotic). Caregivers are overloaded with tasks, most of them physical and repetitive For this reason, caregivers spend a substantial amount of their time in house chores and physical assistance, overlooking social interaction with the assisted elders. Service robots able to perform house chores would relieve caregivers from a significant burden, giving them more time to spend with the elders. Several researchers focus their attention on service robots equipped with manipulators to perform cleaning tasks [32, 42, 25, 15, 31, 9, 33, 41, 22, 24, 21, 14, 27, 7, 8, 26,35, 19, 11, 10, 37, 40, 1, 16, 39, 18, 38]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
