Deep effect trajectory prediction in robot manipulation

Seker, M. Yunus; Tekden, Ahmet E.; Uğur, Emre

doi:10.1016/j.robot.2019.07.003

Cited by 21 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The velocity model of the target motion is often used to predict the state of the system. 19 In the study of target tracking, the target motion model is mainly represented by a state space…”

Section: The Target State Prediction Methods In the Configuration Space Mapmentioning

confidence: 99%

Capturing the dynamic target by the robot manipulator in high-dimensional configuration space map

Zhang

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

In robotics, the tough problem about the dynamic target capturing consists of tracking the target by the robot manipulator and grasping the target by the robot finger. For the sake of space, this article deals with only the first problem, tracking the dynamic target by the robot manipulator. The traditional approaches of capturing the dynamic target may work well when they are employed in low-dimensional space by reinforcement learning or physical modeling. However, they fail to work well in high-dimensional space. The traditional approaches have four limitations with respect to Cartesian space, configuration space, reinforcement learning, and physical modeling. To overcome these limitations, this article implements improved dynamic A* algorithm in high-dimensional configuration space map to capture the target. First, a space injection model injects the collision detection and target position from the Cartesian space into the configuration space to construct a high-dimensional map. Then, the target capturing method including the improved dynamic A* algorithm is applied on the map to track and capture the target. Finally, the experiment performed in time-varying environment and the dynamic target achieves a reliable result. This article has proposed an approach that makes the robot manipulator motion planning more accurate in high-dimensional dynamic configuration space. This approach enables the multi-joint manipulator to avoid the obstacle while tracking the target in high-dimensional configuration space. It takes the advantages of heuristic algorithms in the process of target capturing method designing. It adds precision and speed to target tracking. The success of the approach may apply to any industrial robot tracking target, surgical operation, and space probes. And, it may lay a solid foundation for dynamics control with a scope for future investigations.

show abstract

Section: The Target State Prediction Methods In the Configuration Space Mapmentioning

confidence: 99%

Capturing the dynamic target by the robot manipulator in high-dimensional configuration space map

Zhang

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

show abstract

“…SEMs allow a planner to efficiently plan in the space of diverse skills and parameters, and it also provides two additional benefits: First, because the model is on the skilllevel, not action-level, it only needs one evaluation to predict the effects of a skill execution, which reduces planning time as well as covariate shift by reducing the number of sequential predictions [37], [38], [39], [40]. Second, a longhorizon skill-level model can leverage a skill's ability to act as a funnel in state space during execution, which simplifies the learning problem.…”

Section: B Learning Skill Effect Models (Sems)mentioning

confidence: 99%

Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulation

Liang¹,

Sharma²,

Alex³

et al. 2021

Preprint

View full text Add to dashboard Cite

Lifelong-learning robots need to be able to acquire new skills and plan for new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, like subgoal skills, shared skill implementations, or learning task-specific plan skeletons, that limit their application to new and different skills and tasks. By contrast, we propose doing task planning by jointly searching in the space of skills and their parameters with skill effect models learned in simulation. Our approach is flexible about skill parameterizations and task specifications, and we use an iterative training procedure to efficiently generate relevant data to train such models. Experiments demonstrate the ability of our planner to integrate new skills in a lifelong manner, finding new task strategies with lower costs in both train and test tasks. We additionally show that our method can transfer to the real world without further fine-tuning.

show abstract

“…Recently, Kopicki et al [52] proposed learning multiple motion predictor models for different shaped single objects, where a vision system selects a predictor depending on the context. Seker et al [53] investigated how changing object shapes affects lowlevel object motion trajectories and modeled it using CNNs and LSTMs.…”

Section: Related Workmentioning

confidence: 99%