Human-robot collaboration (HRC) is a widely studied research field that has gained attention during the past few years with the ever-increasing availability of collaborative robots (or cobots). Cobots have the sensing capabilities to actively interact with a human partner toward achieving a common task. Some forms of interaction involve direct physical contact, often referred to as physical human-robot interaction (pHRI). A strong focus of the pHRI-related literature is on ensuring safety during the interaction. Despite the continuous advances in HRC research, applications are few and are usually downgraded to basic workspace sharing rather than actual collaborative work. Taking full advantage of cobots in tasks such as collaborative manipulation of heavy objects or collaborative assembly operations has yet to demonstrate tangible results for the industry, as there is still a need for cobots to operate in an intelligent and adaptive way and be easily programmed by nonexperts. This book includes a series of chapters, presenting some of the latest advances in HRC in an effort to unlock its potential for industrial adoption. The book investigates what the needs of the industry are and what steps should be taken in the research toward efficient, safe, and useful HRC.

The advent of collaborative robots has enabled new applications where human and robots can work together safely and effectively toward achieving a common goal. However, robots in the industry, and particularly in assembly lines, are still programmed with time-consuming methods, have little to no adaptability to changes in the environment, and still present safety issues in close collaboration with a human, due to stiff control methods utilized to achieve accuracy. In this chapter, we address the problem of learning a pick-and-place task by kinesthetic demonstration and executing it to new and even moving targets, aiming at collaborative assembly lines where operations take place on a moving conveyor. Moreover, the human safety aspect is addressed via a control framework that includes two layers. The first layer is in the form of collision avoidance by altering the executed trajectory, and the second one is achieved by a compliant robot behavior that preserves safety under unintentional contacts, without compromising target-reaching accuracy. For the learning part, we modify the traditional dynamic movement primitive (DMP) formulation for properly encoding the demonstrated task and generalizing it spatially to even moving targets. For the performance and safety part, we propose a control structure incorporating the DMP, the human avoidance signals, and the low stiffness controller of the robot to achieve safety and accuracy. Our approach is validated experimentally in a real-world industrial assembly scenario of a TV manufacturer, where a robot and a human collaboratively achieve the assembly of electronic boards on a TV back plate. This work contributes on a wider scale, as it aims to advance the way toward the adoption of human-robot collaboration in industrial assembly lines.

Within the next years, industrial collaborative robots will collaborate with human operators, whose safety might be compromised. To ensure a safe collaboration, robots should estimate the risk of collision with respect to the pose and motion of operators within the shared workspace. A common approach is to compute and maintain a minimum distance between humans and robots during tasks' execution. Nevertheless, separation-based solutions do not capture the real dynamics of the human-robot interaction and tend to be rather conservative, avoiding a close human-robot collaboration. In this chapter, we explore the concept of time-to-contact (TTC) as a softer trigger of safety stops in collaborative scenarios where humans and robots are in constant closeness. Particularly, we propose a TTC formulation and study its advantages with respect to two approaches based on the protective distance proposed by the ISO standards. We compared the three methods in some representative cases extracted from an example of a collaborative task. The evaluation is firstly done in simulation and then in a more realistic setup with a simulated human, aiming for repeatability, and a real robot. Furthermore, we showcased our approach in a demo of a complete collaborative task. TTC allows robots to operate closer to humans and for longer times before a safety stop is issued, which benefits long-term productivity. This later stop produces shorter human-robot distances, which might affect safety. However, the increment in time that the robot moves before stopping (productivity) is far greater than the reduction in the distance (safety). Hence, we can state that TTC greatly improves productivity while slightly compromising safety. In conclusion, our work demonstrates that TTC is a smoother, but still safe, collision risk estimator for close human-robot collaboration.

Physical human-robot interaction (pHRI) is a major challenge in robotics, especially when related to collaborative operations involving the handling of heavy payloads by potentially dangerous robots. In this chapter, we present a sensing architecture designed for shared payload tasks and implemented to accomplish collaborative car windshield manipulation. The pHRI problem is tackled by implementing voluntary contact recognition leveraging data-driven methodologies, ensuring that robot motion is enabled only when the operator is deliberately interacting with the robot. Test bench experiments are eventually presented to show the functionality of the handles along with the integration of the devices on a vacuum gripper for implementation on an industrial robotic manipulator.

Recent advances in robotics have paved the way for the automation of many tasks in the manufacturing industry that were previously performed manually. In particular, through the use of collaborative robots, there are many examples of exciting new applications where humans and robots can work together safely and effectively. However, end-of-line automation, where products are packed into cartons and cartons are placed on pallets, is still done using traditional, time-consuming methods of programming the robot's path and calculating the packing plan. Most importantly, such methods do not incorporate perception and do not take full advantage of a robot's capabilities for a flexible automation cell. For example, in a manufacturing line with frequent batch production changes, packing a different product requires reprogramming of the robot.

In this chapter, we propose a versatile solution for automating dense packing tasks in an industrial environment using teaching by demonstration and 3D vision. Teaching enables the user to create the robot's pick-and-place motion pattern in a very short time and without any programming effort. 3D vision with AI gives the robot the ability to recognize its environment, adapt its movements, and remain safe for humans. The system is able to accurately detect and track objects moving on a conveyor by proposing a novel vision pipeline that has high accuracy and can handle partial or complete occlusion of objects by the robot's body. In addition, the system can detect humans in the robot's workspace and adjust the robot's speed to maintain the minimum distance between the robot arm and the human body. We validate the system in a series of experiments with a dense packing task. Our goal is a portable and flexible robotic cell that can be taught by personnel on the production line how to pack products quickly and easily.

This book has provided an overview of the latest research and developments in the field of human-robot collaboration, with a particular focus on the potential for industrial adoption. By working together, robots and humans can take advantage of each other's strengths and complement each other's abilities. This will become increasingly important as Industry 5.0, which focuses on the cooperation between humans and machines, becomes more prevalent.