An application of reinforcement learning algorithms to industrial multi-robot stations for cooperative handling operation

Schwung, Dorothea; Csaplar, Fabian; Schwung, Andreas; Ding, Steven X.

doi:10.1109/indin.2017.8104770

Cited by 14 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e application of manipulators makes production more efficient and flexible. e core issue of automatic manipulator tracking control is how to ensure the given moving target follows the expected trajectory and adapts to various uncertain factors [7][8][9][10][11]. It is of great practical significance to derive an automatic tracking control strategy for moving targets under uncertainties and external interference.…”

Section: Introductionmentioning

confidence: 99%

Automatic Manipulator Tracking Control Based on Moving Target Trajectory Prediction

Luo

2021

Scientific Programming

View full text Add to dashboard Cite

The core issue of automatic manipulator tracking control is how to ensure the given moving target follows the expected trajectory and adapts to various uncertain factors. However, the existing moving target trajectory prediction methods rely on highly complex and accurate models, lacking the ability to generalize different automatic manipulator tracking scenarios. Therefore, this study tries to find a way to realize automatic manipulator tracking control based on moving target trajectory prediction. In particular, a moving target trajectory prediction model was established, and its parameters were optimized. Next, a tracking-training-testing algorithm was proposed for manipulator’s automatic moving target tracking, and the operating flows were detailed for training module, target detection module, and target tracking module. The proposed model and algorithm were proved effective through experiments.

show abstract

Section: Introductionmentioning

confidence: 99%

Automatic Manipulator Tracking Control Based on Moving Target Trajectory Prediction

Luo

2021

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…Reinforcement learning applied to multi-agent systems has two dimensions: DRL algorithms that model policies for multiagent control and interaction, and DRL approaches that rely on multiple agents to parallelize the learning process or explore a wider variety of experiences. Within the former category, we can find examples of DRL for formation control [6], obstacle and collision avoidance [7], [8], collaborative assembly [9], or cooperative multi-agent control in general [10]. In the latter category, most existing approaches refer to the utilization of multiple agents to learn in parallel, but from the point of view of a multi-process or multi-threaded application [3].…”

Section: Introductionmentioning

confidence: 99%

Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning

Zhao

Queralta

et al. 2020

2020 5th International Conference on Robotics and Automation Engineering (ICRAE)

View full text Add to dashboard Cite

Current research directions in deep reinforcement learning include bridging the simulation-reality gap, improving sample efficiency of experiences in distributed multi-agent reinforcement learning, together with the development of robust methods against adversarial agents in distributed learning, among many others. In this work, we are particularly interested in analyzing how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems where the operation of the different robots is not necessarily homogeneous. These variations can happen due to sensing mismatches, inherent errors in terms of calibration of the mechanical joints, or simple differences in accuracy. While our results are simulation-based, we introduce the effect of sensing, calibration, and accuracy mismatches in distributed reinforcement learning with proximal policy optimization (PPO). We discuss on how both the different types of perturbances and how the number of agents experiencing those perturbances affect the collaborative learning effort. The simulations are carried out using a Kuka arm model in the Bullet physics engine. This is, to the best of our knowledge, the first work exploring the limitations of PPO in multi-robot systems when considering that different robots might be exposed to different environments where their sensors or actuators have induced errors. With the conclusions of this work, we set the initial point for future work on designing and developing methods to achieve robust reinforcement learning on the presence of realworld perturbances that might differ within a multi-robot system.

show abstract

“…In this paper, the RL algorithm is used to optimise the weighting parameters using the method of mutual learning between weight parameters and DMR. RL has been applied to electric vehicle dispatching [21], transportation planning [22], power systems [23], robot control [24,25], and other problems. It has achieved impressive results in the fields of unmanned cars [26] and games [27,28].…”

Section: Introductionmentioning

confidence: 99%

Research on parameter optimisation of dynamic priority scheduling algorithm based on improved reinforcement learning

Meng

Zhu

Xia

et al. 2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

An application of reinforcement learning algorithms to industrial multi-robot stations for cooperative handling operation

Cited by 14 publications

References 12 publications

Automatic Manipulator Tracking Control Based on Moving Target Trajectory Prediction

Automatic Manipulator Tracking Control Based on Moving Target Trajectory Prediction

Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning

Research on parameter optimisation of dynamic priority scheduling algorithm based on improved reinforcement learning

Contact Info

Product

Resources

About