Trajectory modification of a cloud learning robot

Song, Kai‐Tai; Song, Shao-Huan; Liu, Hung-Shen

doi:10.1109/cacs.2017.8284262

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where not all sensing, computation, and memory is integrated into a single standalone system and presented four potential benefits from the cloud robotics, one of which is about collective robot learning that enables robots to share trajectories, control laws and outcomes through cloud computing . Some research about grasping (Mahler et al , 2016), SLAM technology (Kamburugamuve et al , 2016) and trajectory modification (Song et al , 2017) took advantages of big data, cloud computing and data sharing through the cloud data set to reduce calculation consumption. While others drew attention on building cloud robotic systems (Manzi et al , 2017 , Wan et al , 2016) and database for object grasping (Kent et al , 2011; Goldfeder et al , 2009), mobile robot navigation and robotic autonomous assembling (Waibel et al , 2011).…”

Section: Introductionmentioning

confidence: 99%

“…Qiao et al (2014) proposed a concept of “attractive region in environment” and used it for high-precision tasks with low-precision system. Except for learning from robotic simulation, some researchers studied imitation learning or programming from demonstration technology for cloud-based applications, such as Song et al (2017) studied cloud-based robot learning for trajectory modification and certification by using two robots (a dual-arm home service robot and a TM5 robot). Du et al (2020) used imitated learning for robotic learning based on incorporated incremental learning and meta learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic movement primitives based cloud robotic skill learning for point and non-point obstacle avoidance

Wang

2021

View full text Add to dashboard Cite

Purpose Dynamic movement primitives (DMPs) is a general robotic skill learning from demonstration method, but it is usually used for single robotic manipulation. For cloud-based robotic skill learning, the authors consider trajectories/skills changed by the environment, rebuild the DMPs model and propose a new DMPs-based skill learning framework removing the influence of the changing environment. Design/methodology/approach The authors proposed methods for two obstacle avoidance scenes: point obstacle and non-point obstacle. For the case with point obstacles, an accelerating term is added to the original DMPs function. The unknown parameters in this term are estimated by interactive identification and fitting step of the forcing function. Then a pure skill despising the influence of obstacles is achieved. Using identified parameters, the skill can be applied to new tasks with obstacles. For the non-point obstacle case, a space matching method is proposed by building a matching function from the universal space without obstacle to the space condensed by obstacles. Then the original trajectory will change along with transformation of the space to get a general trajectory for the new environment. Findings The proposed two methods are certified by two experiments, one of which is taken based on Omni joystick to record operator’s manipulation motions. Results show that the learned skills allow robots to execute tasks such as autonomous assembling in a new environment. Originality/value This is a new innovation for DMPs-based cloud robotic skill learning from multi-scene tasks and generalizing new skills following the changes of the environment.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic movement primitives based cloud robotic skill learning for point and non-point obstacle avoidance

Wang

2021

View full text Add to dashboard Cite

show abstract

A New Cloud Robots Training Method Using Cooperative Learning

Wang

Li³

2020

IEEE Access

View full text Add to dashboard Cite

At present, cloud robots tend to be intelligent and cooperative. Based on this, we proposed a teaching method based on Imitation and a learning method that incorporates Incremental Learning and Meta Learning. We use Imitation Learning to teach robots, and more concretely, we propose a natural teaching method based on visual sense by using a depth camera, the robot can learn from the trajectory caught by the camera. Meta Learning helps robots understand the task and split it into some subtasks which enhances the level of generalization. Besides, once the circumstances change the robot can update the cloud database using Incremental Learning. Using proposed method, we make robots capable of learning and cooperating with other robots. It is no longer necessary for robots to learn based on a great number of data which is a shortcoming of traditional robots. The greatest advantage of this method is that we improve the learning efficiency of robots and enhance the level of generalization of the model. Our method was experimentally verified in a laboratory and the results indicated that the method improved the learning efficiency of robots. INDEX TERMS Imitation learning, cloud robot, incremental learning, meta learning.

show abstract

Trajectory modification of a cloud learning robot

Cited by 2 publications

References 11 publications

Dynamic movement primitives based cloud robotic skill learning for point and non-point obstacle avoidance

Dynamic movement primitives based cloud robotic skill learning for point and non-point obstacle avoidance

A New Cloud Robots Training Method Using Cooperative Learning

Contact Info

Product

Resources

About