Artificial intelligence planners for multi-head path planning of SwarmItFIX agents

Veeramani, S.; Muthuswamy, Sreekumar; Sagar, Keerthi; Zoppi, Matteo

doi:10.1007/s10845-019-01479-8

Cited by 8 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of manufacturing, reinforcement learning methods have been proposed for model-free adaptive optimization on the device level and the operational level of various manufacturing processes. Recently published work include the optimization of process control in sheet metal milling (Veeramani et al 2019), polymerization reaction systems (Ma et al 2019), laser welding (Günther et al 2016) and in deep drawing (Dornheim et al 2019). Operational optimization objects are amongst others material flow in industrial mining (Kumar et al 2020), preventive maintenance scheduling of flow line systems (Wang et al 2016) and job shop scheduling (Kuhnle et al 2020).…”

Section: Contributionmentioning

confidence: 99%

Deep reinforcement learning methods for structure-guided processing path optimization

et al. 2021

View full text Add to dashboard Cite

A major goal of materials design is to find material structures with desired properties and in a second step to find a processing path to reach one of these structures. In this paper, we propose and investigate a deep reinforcement learning approach for the optimization of processing paths. The goal is to find optimal processing paths in the material structure space that lead to target-structures, which have been identified beforehand to result in desired material properties. There exists a target set containing one or multiple different structures, bearing the desired properties. Our proposed methods can find an optimal path from a start structure to a single target structure, or optimize the processing paths to one of the equivalent target-structures in the set. In the latter case, the algorithm learns during processing to simultaneously identify the best reachable target structure and the optimal path to it. The proposed methods belong to the family of model-free deep reinforcement learning algorithms. They are guided by structure representations as features of the process state and by a reward signal, which is formulated based on a distance function in the structure space. Model-free reinforcement learning algorithms learn through trial and error while interacting with the process. Thereby, they are not restricted to information from a priori sampled processing data and are able to adapt to the specific process. The optimization itself is model-free and does not require any prior knowledge about the process itself. We instantiate and evaluate the proposed methods by optimizing paths of a generic metal forming process. We show the ability of both methods to find processing paths leading close to target structures and the ability of the extended method to identify target-structures that can be reached effectively and efficiently and to focus on these targets for sample efficient processing path optimization.

show abstract

Section: Contributionmentioning

confidence: 99%

Deep reinforcement learning methods for structure-guided processing path optimization

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Finally, required angles ( sm θ k,w ) of all the manipulator joints for all the waypoints are determined with the help of an optimization-based inverse kinematics model given in Eqs. (2)(3)(4)(5). Where, Eq.…”

Section: Trajectory Planning Of Comau Ns16mentioning

confidence: 99%

“…The workspace of these SwarmItFIX platform can be modified by varying the size of the workbenches or by increasing the number of docking pins. The details of the SwarmItFIX setup and the agent coordination have been described in detail in the previous works of the authors [2][3][4]. A software framework called MRROC++ has been utilized for the path planning of robot systems including ASEA IRB 6 and SwarmItFIX [5].…”

Section: Introductionmentioning

confidence: 99%

Hybrid type multi-robot path planning of a serial manipulator and SwarmItFIX robots in sheet metal milling process

Veeramani

Muthuswamy

2021

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

This work investigates on the coordinated locomotion between a ceiling-mounted serial manipulator and two SwarmItFIX robots. The former holds the machining tool as an end effector, and the other two robots act as swarm robotic fixtures in a sheet metal milling process. A novel offline coordination planner which follows the hierarchical based hybrid type decentralized planning strategy has been proposed. Motion of the serial manipulator and SwarmItFIX robots’ coordinated locomotion are divided into three sub-problems, viz, trajectory planning of serial manipulator, task planning of SwarmItFIX robots, and homogenous prioritized multi-robot path planning of SwarmItFIX robots. Mathematical formulation of all the three sub-problems is developed and presented in this paper. A hexagonal segment that fits inside the boundaries of the workspace is considered as the machining trajectory. The tool velocity is assumed to be constant as it improves the quality of machining. The results obtained from the proposed planner is found to be efficient as the task planning module has computed the precise support locations and support duration for the SwarmItFIX robots. The multi-robot path planning module of the planner computes the optimal collision-free paths of SwarmItFIX robots for all goal positions. Finally, trajectories of SwarmItFIX robots are found to be completely in-line with the trajectory of tool center point (TCP) of the serial manipulator.

show abstract

“…The novel Swing and Dock (SaD) locomotion strategy of the mobile base has already been explained in the previous works. [15][16][17] Head is a vacuum type of end effector used to support the sheet metal on its bottom surface. For the head to reach the specific coordinate within the workspace, the cooperation of all the three agents become essential.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement learning based path planning of multiple agents of SwarmItFIX robot for fixturing operation in sheetmetal milling process

Veeramani

Muthuswamy

2022

Proceedings of the Institution of Mechanical Engineers, Part B:

Self Cite

View full text Add to dashboard Cite

SwarmItFIX (self-reconfigurable intelligent swarm fixtures) is a multi-agent setup mainly used as a robotic fixture for large Sheet metal machining operations. A Constraint Satisfaction Problem (CSP) based planning model is utilized currently for computing the locomotion sequence of multiple agents of the SwarmItFIX. But the SwarmItFIX faces several challenges with the current planner as it fails on several occasions. Moreover, the current planner computes only the goal positions of the base agent, not the path. To overcome these issues, a novel hierarchical planner is proposed, which employs Monte Carlo and SARSA TD based model-free Reinforcement Learning (RL) algorithms for the computation of locomotion sequences of head and base agents, respectively. These methods hold two distinct features when compared with the existing methods (i) the transition model is not required for obtaining the locomotion sequence of the computational agent, and (ii) the state-space of the computational agent become scalable. The obtained results show that the proposed planner is capable of delivering optimal makespan for effective fixturing during the sheet metal milling process.

show abstract

Artificial intelligence planners for multi-head path planning of SwarmItFIX agents

Cited by 8 publications

References 27 publications

Deep reinforcement learning methods for structure-guided processing path optimization

Deep reinforcement learning methods for structure-guided processing path optimization

Hybrid type multi-robot path planning of a serial manipulator and SwarmItFIX robots in sheet metal milling process

Reinforcement learning based path planning of multiple agents of SwarmItFIX robot for fixturing operation in sheetmetal milling process

Contact Info

Product

Resources

About