Collaborative programming of robotic task decisions and recovery behaviors

Abstract

Programming by demonstration is reaching industrial applications, which allows non-experts to teach new tasks without manual code writing. However, a certain level of complexity, such as online decision making or the definition of recovery behaviors, still requires experts that use conventional programming methods. Even though, experts cannot foresee all possible faults in a robotic application. To encounter this, we present a framework where user and robot collaboratively program a task that involves online decision making and recovery behaviors. Hereby, a task-graph is created that represents a production task and possible alternative behaviors. Nodes represent start, end or decision states and links define actions for execution. This graph can be incrementally extended by autonomous anomaly detection, which requests the user to add knowledge for a specific recovery action. Besides our proposed approach, we introduce two alternative approaches that manage recovery behavior programming and compare all approaches extensively in a user study involving 21 subjects. This study revealed the strength of our framework and analyzed how users act to add knowledge to the robot. Our findings proclaim to use a framework with a task-graph based knowledge representation and autonomous anomaly detection not only for initiating recovery actions but particularly to transfer those to a robot.

A Practical Roadmap to Learning from Demonstration for Robotic Manipulators in Manufacturing

“…Tasks that involve collaborating with humans or other robots typically provide interaction through an observation or interaction interface, which serves as a channel for information exchange between the robot and its collaborators [37,[69][70][71][72][73]. These interfaces can take various forms, such as physical interaction mechanisms or dedicated communication protocols [72,[74][75][76], and are specifically designed and tailored to facilitate the collaborative task.…”

“…Kinesthetic teaching is a method wherein a human guides a robot through a desired motion within the robot's configuration space. In this approach, a human physically guides the robot to perform a task, and the robot records the demonstration using its joint sensors (Figure 5a) [15,32,36,37,50,52,56,58,71,[90][91][92][93]. The key aspect is the direct interaction between the human teacher and the robot in the robot's configuration space.…”

“…Another trend for improving robustness is focused on the robustness against various disturbances and errors through out the LfD cycle [33,54,71]. The work in [71] has focused on the fact that while LfD can allow non-experts to teach new tasks in industrial manufacturing settings, exerts are still required to program fault recovery behaviors. They have proposed a framework where robots autonomously detect an anomaly in execution and learn how to tackle that anomaly by collaborating with human.…”

Novel Approach Using Risk Analysis Component to Continuously Update Collaborative Robotics Applications in the Smart, Connected Factory Model

“…For example, depending on the objects to be manipulated, different end-effectors (EE) and picking strategies might be required [13][14][15]. Consequently, different programming strategies [16] or types of collaboration, such as the ones shown in Figure 1, might be necessary. Furthermore, the human collaborating with the robot might have different requirements in terms of ergonomic needs and workplace safety [17].…”