Search

A conventional adopted method for operating a waiter robot is based on the static position control, where predefined goal positions are marked on a map. However, this solution is not optimal in a dynamic setting, such as in a coffee shop or an outdoor catering event, because the customers often change their positions. This article explores an alternative human-robot interface design where a human operator communicates the identity of the customer to the robot instead. Inspired by how human communicates, we propose a framework for communicating a visual goal to the robot, through interactive two-way communications. The framework exploits concepts from two machine learning domains: human-in-the-loop machine learning, where active learning is used to acquire informative data, and deep metric learning, where a suitable embedding can improve the learning ability of a classifier. We also propose novel class imbalance handling techniques, which aim to actively alleviate the class imbalance problem found to be important in this mode of communication. The framework is evaluated using publicly available pedestrian datasets. We demonstrate that the proposed framework can help reduce the number of required two-way interactions and increases the robustness of the predictive model. We successfully implement the framework on a mobile robot for a delivery service in a cafe-like environment. Through the online visual goal human-robot communication, the robot can detect, recognize, and autonomously navigate to the target customer.

Adaptive systems enable legged robots to cope with a wide range of environmental settings and unforeseen events. Existing reactive methods adapt either the walking frequency or the amplitude to only simple perturbations. This letter proposes an adaptive mechanism for central pattern generator (CPG)-based locomotion control that online-reacts to both internal and external soft constraints by adapting both the frequency and amplitude of driving signals. Our approach, namely GRAdient-Based shape adaptive control (GRAB), utilises real-time sensory signals for adapting the dynamics of the CPG. GRAB reacts to locomotion soft constraints given in a loss function. It can quickly adapt CPG’s dynamics variables to reduce such a loss, with a gradient-descent-like update step. The update perturbs the shape of the driving signal, which implicitly changes both frequency and amplitude of the robot locomotion pattern. We test the GRAB mechanism on a hexapod robot and its simulation, where we demonstrate its several benefits over a state-of-the-art adaptive control baseline. First, we show that it can be used for reducing the tracking error by simultaneously changing the walking amplitude and frequency. Also, GRAB can be used for limiting the maximum torque/current, preventing motor damage from unexpected perturbations. Finally, we demonstrate how GRAB can be utilised to naturally adjust the robot’s walking speed while taking into account multiple constraints, including target walking speed, external weight perturbations, and the robot’s physical limit.

Objective: Advances in the motor imagery (MI)-based brain-computer interfaces (BCIs) allow control of several applications by decoding neurophysiological phenomena, which are usually recorded by electroencephalography (EEG) using a non-invasive technique. Despite significant advances in MI-based BCI, EEG rhythms are specific to a subject and various changes over time. These issues point to significant challenges to enhance the classification performance, especially in a subjectindependent manner. Methods: To overcome these challenges, we propose MIN2Net, a novel end-to-end multi-task learning to tackle this task. We integrate deep metric learning into a multi-task autoencoder to learn a compact and discriminative latent representation from EEG and perform classification simultaneously. Results: This approach reduces the complexity in pre-processing, results in significant performance improvement on EEG classification. Experimental results in a subject-independent manner show that MIN2Net outperforms the state-of-the-art techniques, achieving an F1-score improvement of 6.72% and 2.23% on the SMR-BCI and OpenBMI datasets, respectively. Conclusion: We demonstrate that MIN2Net improves discriminative information in the latent representation. Significance: This study indicates the possibility and practicality of using this model to develop MI-based BCI applications for new users without calibration. This work was supported in part by PTT Public Company Limited, in part by The SCB Public Company Limited, in part by Thailand Science Research, and Innovation under Grant SRI62W1501, in part by The Office of the Permanent Secretary of the Ministry of Higher Education, Science, Research, and Innovation, Thailand under Grant RGNS63-252, and in part by the National Research Council of Thailand under Grant N41A640131.