A Real-Time Receding Horizon Sequence Planner for Disassembly in a Human-Robot Collaboration Setting

Abstract

Product disassembly is a labor-intensive process and is far from being automated. Typically, disassembly is not robust enough to handle product varieties from different shapes, models, and physical uncertainties due to component imperfections, damage throughout component usage, or insufficient product information. To overcome these difficulties and to automate the disassembly procedure through human-robot collaboration without excessive computational cost, this paper proposes a real-time receding horizon sequence planner that distributes tasks between robot and human operator while taking real-time human motion into consideration. The sequence planner aims to address several issues in the disassembly line, such as varying orientations, safety constraints of human operators, uncertainty of human operation, and the computational cost of large number of disassembly tasks. The proposed disassembly sequence planner identifies both the positions and orientations of the to-be-disassembled items, as well as the locations of human operator, and obtains an optimal disassembly sequence that follows disassembly rules and safety constraints for human operation. Experimental tests have been conducted to validate the proposed planner: the robot can locate and disassemble the components following the optimal sequence, and consider explicitly human operator’s real-time motion, and collaborate with the human operator without violating safety constraints.

Task allocation and planning for product disassembly with human–robot collaboration

“…Motion planning Prevent collision via planning robot motion in real time [12], [16], [18], [21], [22], [24], [33], [34] Task planning Develop safety measures by considering factors such as hazardous components and working distances and assign tasks accordingly [14], [15], [23] disassembly cost, ultimately leading to the generation of an optimal HRC disassembly sequence.…”

“…HRC makes the disassembly collaboration modes more complex than those without robots. Briefly, collaboration modes can be classified into three types: sequential [13]- [15], parallel [12], [16]- [20], and collaborative [21]- [24], as summarized in Table I.…”

“…Each workstation consisted of a human operator and a robot, and the workers performed disassembly tasks one after the other. Additionally, in [15], [27], a receding-horizon sequence planner was proposed to distribute disassembly tasks to a human operator or a robot while factoring in real-time human motion. The planner traversed feasible task sequences and obtained the optimal one for the next three disassembly steps.…”

“…The attributes included moving complexity, workload, hazardous level, etc. In [14] and [15], the geometric complexity and the labor efforts of the to-be-disassembled components were considered as the disassembly cost in finding the HRC optimal disassembly sequence.…”

3D-PDNet: Automated Product Disassembly Sequence Planning

“…Over the years, the problem of disassembly sequence planning (DSP) has been explored using different methods to generate a feasible sequence automatically. To generate a feasible DSP, traditional approaches use optimization-based methods, including mathematical programming (e.g., optimizing a cost function using linear programming [15]); others typically use search methods with heuristic rules to prune the search space and speed up the search process [5]. Another set of work includes the use of evolutionary algorithms like genetic algorithm [21], and its variants (e.g.…”