Robotics: Human-Robot Interaction - Theory and applications

A brief introduction of a feedback control system for robotic applications is presented, and each of its constituent parts is explained. We talk about sensors, types of control algorithms, and mathematical models of robots.

This video presents the classification of robots according to their environment, interaction mechanism, and field of application.

Different types of robots are briefly introduced, for example humanoid, zoomorphic, mobile, autonomous vehicles, manipulator robots, robotic exoskeletons, consumer robots, educational robots, and service robots.

Brief introduction to Human-Robot Interaction with examples oriented to the type of physical, cognitive and social interaction.

Topics related to remote interaction, proximity interaction, teleoperation, and telemanipulation are reviewed.

The third type of interaction is explained which is social interaction. In addition, the person's social interaction zones are explained. It also explains how a robot should consider a person's range of vision to approach it in a socially acceptable way.

Each stage of a social interaction architecture for a mobile robot that uses non-verbal communication techniques is described.

An example of application of the architecture of social interaction for a mobile robot that uses non-verbal communication techniques is explained, in which cases of evasion, approach, and tracking of a human are considered.

It briefly explains about the first guidelines of the HRI, as well as its evolution since the 1990s.

We define what defines an HRI system. The key aspects of an HRI system are presented.

Types of interface, and types of communication between the human and the robot are analyzed.

A brief analysis of the productivity and profitability of examples of processes using only humans, using only robots, and using humans collaborating with robots is presented.

In this video, we talk about safety for cooperative systems. ISO and ANSI standards are briefly explained, and general safety recommendations recommended for HRI systems are indicated.

In this video, an example of an HRI system application is analyzed, and it is explained step by step from the point of view of the general concepts learned.

The six different types of metrics that are used to characterize HRI systems are listed.

Metrics for HRI systems based on mission effectiveness are explained in this video. In particular, time-based metrics, error metrics, and coverage metrics are explained.

In this video, metrics related to the efficiency of human behavior, human cognitive indicators, human physiological indicators, and human psychological indicators are analyzed.

In this video, metrics related to the behavior of the robot are analyzed, such as its effectiveness and efficiency, robustness, level of autonomy, learning capacity, adaptability, self-awareness, and human awareness.

The negligence tolerance metric is analyzed, which indicates how the effectiveness of a collaborative task decreases when a human neglects it, leaving the robot alone. It is also analyzed what happens when the complexity of the task increases. This metric is often used to measure the level of autonomy of a robot.

The interaction effort metric of the robot is analyzed in detail.

The robot attention demand metric is analyzed in detail.

The free time metric of a human when interacting with a robot is analyzed in detail.

The fan-out metric is explained in detail. It analyzes the effectiveness of a cooperative task by increasing the number of robots with which a human interacts during a cooperative task.

Human-robot team behavior action efficiency metrics are analyzed.

Human-robot team cognition efficiency metrics are analyzed.

Example of application of various metrics for a human collaborating with a robot manipulator and a mobile robot.

Example of application of various metrics for a human collaborating with a robot manipulator and a mobile robot.

Example of application of various metrics for a human collaborating with a robot manipulator and a mobile robot.

Example of application of various metrics for a human collaborating with a robot manipulator and a mobile robot.

Design concepts related to HRI systems are analyzed. The level of autonomy is analyzed, and the difference between the level of autonomy of the Sheridan scale with respect to the level of autonomy for HRI systems is studied.

Three different models of robot architectures that can be used in HRI systems and their benefits are reviewed.

The concepts of the nature of information exchange, adaptation, definition of tasks, and structure of the human-robot team are analyzed.

Design concepts related to HRI systems applied to an example are reviewed. The level of autonomy is analyzed, and the difference between the level of autonomy of the Sheridan scale with respect to the level of autonomy for HRI systems is studied.

Three different architecture models for robots that can be used in HRI systems and their benefits are reviewed with examples.

The concepts of the nature of information exchange, adaptation, task shaping, and structure of the human-robot team are analyzed with an example.

Guidelines for designing the taxonomy of an HRI system are indicated.

Based on an example, it is indicated how to apply the guidelines to design the taxonomy of an HRI system.

Human factors such as workload, situational awareness, reliance on automation, human mental models, and various human cognitive factors such as sleepiness and stress level are analyzed.

This video analyzes with an example how a person's workload can be measured, as well as various other load indices when performing a task.

In this video, the situational awareness of the human and the robot is analyzed with an example, as well as a possible model for this parameter. In addition, trust in automation parameters and mental models are also discussed.

This video analyzes with an example how several cognitive factors of the human could be obtained, such as sleepiness, sleep quality, and stress, among others. These parameters can be used to help reduce human error and accidents in certain processes and applications.

The difference between artificial intelligence, machine learning, and deep learning is reviewed in a general manner since these are very useful areas for HRI.

A brief summary of the main machine and deep learning techniques is made, and a possible application of supervised learning related to computer vision is reviewed. The analyzed techniques have several applications for HRI systems, including the detection of the person and their cognitive parameters.

In this video, a case study for a scooter-type mobile assistance robot is analyzed. The main idea is that the robot detects the cognitive parameters of the human using deep learning techniques. If the human is not able to continue driving, then the robot gradually takes control of the vehicle, thus changing its level of autonomy.

In this video, a case study for a scooter-type mobile assistance robot is analyzed. The main idea is that the robot detects the cognitive parameters of the human using deep learning techniques. If the human is not able to continue driving, then the robot gradually takes control of the vehicle, thus changing its level of autonomy.