Contact driven tasks, such as surface conditioning operations (wiping, polishing, sanding, etc.), are difficult to program in advance to be performed autonomously by a robotic system, specially when the objects involved are moving. In many applications, human-robot physical interaction can be used for the teaching, specially in learning from demonstrations frameworks, but this solution is not always available. Robot teleoperation is very useful when user and robot cannot share the same workspace due to hazardous environments, inaccessible locations, or because of ergonomic issues. In this sense, this paper introduces a novel dual-arm teleoperation architecture with haptic and visual feedback to enhance the operator immersion in surface treatment tasks. Two task-based assistance systems are also proposed to control each robotic manipulator individually. To validate the remote assisted control, some usability tests have been carried out using Baxter, a dual-arm collaborative robot. After analysing several benchmark metrics, the results show that the proposed assistance method helps to reduce the task duration and improves the overall performance of the teleoperation.

High dexterity is required in tasks in which there is contact between objects, such as surface conditioning (wiping, polishing, scuffing, sanding, etc.), specially when the location of the objects involved is unknown or highly inaccurate because they are moving, like a car body in automotive industry lines. These applications require the human adaptability and the robot accuracy. However, sharing the same workspace is not possible in most cases due to safety issues. Hence, a multi-modal teleoperation system combining haptics and an inertial motion capture system is introduced in this work. The human operator gets the sense of touch thanks to haptic feedback, whereas using the motion capture device allows more naturalistic movements. Visual feedback assistance is also introduced to enhance immersion. A Baxter dual-arm robot is used to offer more flexibility and manoeuvrability, allowing to perform two independent operations simultaneously. Several tests have been carried out to assess the proposed system. As it is shown by the experimental results, the task duration is reduced and the overall performance improves thanks to the proposed teleoperation method.

This paper presents an obstacle avoidance technique for a mobile robot in human-robot collaborative (HRC) tasks. The proposed solution uses fuzzy logic rules and a convolutional neural network (CNN) in an integrated approach to detect objects during vehicle movement. The goal is to improve the robot’s navigation autonomously and ensure the safety of people and equipment in dynamic environments. Using this technique, it is possible to provide important references to the robot’s internal control system, guiding it to continuously adjust its velocity and yaw in order to avoid obstacles (humans and moving objects) while following the path planned for its task. The approach aims to improve operational safety without compromising productivity, addressing critical challenges in collaborative robotics. The system was tested in a simulated environment using the Robot Operating System (ROS) and Gazebo to demonstrate the effectiveness of navigation and obstacle avoidance. The results obtained with the application of the proposed technique indicate that the framework allows real-time adaptation and safe interaction between robot and obstacles in complex and changing industrial workspaces.

Learning Assistance by Demonstration (LAD) is concerned with using demonstrations of a human agent to teach a robot how to assist another human. The concept has previously been used with smart wheelchairs to provide customised assistance to individuals with driving difficulties. A basic premise of this technique is that the learned assistive policy should be able to generalise to environments different than the ones used for training; but this has not been tested before. In this work we evaluate the assistive power and the generalisation capability of LAD using our custom teleoperation and learning system for smart wheelchairs, while seeking to improve it by experimenting with different combinations of dimensionality reduction techniques and machine learning models. Using Autoencoders to reduce the dimension of laserscan data and a Gaussian Process as the learning model, we achieved a 23% improvement in prediction performance against the combination used by the latest work on the field. Using this model to assist a driver exposed to a simulated disability, we observed a 9.8% reduction in track completion times when compared to driving without assistance.