Towards robust human-robot mobile co-manipulation for tasks involving the handling of non-rigid materials using sensor-fused force-torque, and skeleton tracking data

Schepper, David De; Moyaers, Bart; Schouterden, Gert; Kellens, Karel; Demeester, Eric

doi:10.1016/j.procir.2020.05.245

Cited by 18 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 4: Initialization operation. (1) Randomly assign values to the population for initialization operations based on the speed constraint (28) and add the opposing population generated by the inverse learning method (29) into the initial population. Step 5: Mutation operation.…”

Section: Solving the Trajectory Tracking Problemmentioning

confidence: 99%

See 1 more Smart Citation

Control of Trajectory Tracking for Mobile Manipulator Robot with Kinematic Limitations and Self-Collision Avoidance

2022

View full text Add to dashboard Cite

In this paper, we propose an optimized differential evolution algorithm based on kinematic limitations and structural complexity constraints to solve the trajectory tracking problem for a mobile manipulator robot. The traditional method mainly involves obtaining the speed of the control variable based on the Jacobian inverse or linearization of the robot’s kinematic model, which cannot avoid the singularity position and/or self-collision phenomena. To address these problems, we directly design an optimized differential evolution algorithm to solve the trajectory planning problem for mobile manipulator robots. First, we analyze various constraints on the actual movement and describe them specifically using various equations or inequalities, including non-holonomic constraints on the mobile platform, the physical limitations of the driving motors, self-collision avoidance restriction, and smoothly traversing the singularity position. Next, we re-define the trajectory tracking of a mobile manipulator robot as an optimization problem under multiple constraints, including the trajectory tracking task and various constraints simultaneously. Then, we propose a new differential evolution (DE) algorithm by optimizing some critical operations to solve the optimization problem, such as improving the population’s distribution, limiting the population distribution range, and adding a success index. Additionally, we design two simple trajectories and two complex trajectories to determine the performance of the optimized DE algorithm in solving the trajectory tracking problem. The results demonstrate that the optimized DE algorithm can effectively realize the high-precision trajectory tracking task of a differential wheeled mobile manipulator robot through the consideration of kinematic limitations and self-collision avoidance.

show abstract

Section: Solving the Trajectory Tracking Problemmentioning

confidence: 99%

“…The mobile manipulator robots have gradually become mainstream robots; they combine the mobile platform and the manipulator robot to allow for the completion of complex tasks [1,2]. Compared with fixed manipulator and single mobile robots, mobile manipulator robots can utilize a larger workspace and have advanced dexterity [3,4].…”

Section: Introductionmentioning

confidence: 99%

Control of Trajectory Tracking for Mobile Manipulator Robot with Kinematic Limitations and Self-Collision Avoidance

2022

View full text Add to dashboard Cite

show abstract

“…Thus, estimating the deformation state only by force and torque measurements is challenging. Consequently, standard control architectures based on impedance or admittance control cannot be used directly De Schepper, Moyaers, Schouterden, Kellens, and Demeester (2021); Sirintuna, Giammarino, and Ajoudani (2022).…”

Section: Introductionmentioning

confidence: 99%

Co-manipulation of soft-materials estimating deformation from depth images

Nicola¹,

Villagrossi²,

Pedrocchi³

2023

Preprint

View full text Add to dashboard Cite

Human-robot co-manipulation of soft materials, such as fabrics, composites, and sheets of paper/cardboard, is a challenging operation that presents several relevant industrial applications. Estimating the deformation state of the co-manipulated material is one of the main challenges. Viable methods provide the indirect measure by calculating the human-robot relative distance. In this paper, we develop a datadriven model to estimate the deformation state of the material from a depth image through a Convolutional Neural Network (CNN). First, we define the deformation state of the material as the relative rototranslation from the current robot pose and a human grasping position. The model estimates the current deformation state through a Convolutional Neural Network, specifically a DenseNet-121 pretrained on ImageNet. The delta between the current and the desired deformation state is fed to the robot controller that outputs twist commands. The paper describes the developed approach to acquire, preprocess the dataset and train the model. The model is compared with the current state-of-the-art method based on a skeletal tracker from cameras. Results show that our approach achieves better performances and avoids the various drawbacks caused by using a skeletal tracker. Finally, we also studied the model performance according to different architectures and dataset dimensions to minimize the time required for dataset acquisition.

show abstract

“…Robotic part transportation is a compelling application as many industrial sectors such as the aeronautic [ 3 , 4 ] or automotive [ 5 , 6 ] require moving large parts among different areas of the workshops, using a large amount of the workforce on tasks with no added value. Therefore, the design and development of collaborative solutions based on flexible robotic systems able to transport large pieces [ 7 , 8 , 9 ] would benefit a wide range of companies worldwide.…”

Section: Introductionmentioning

confidence: 99%

Path Driven Dual Arm Mobile Co-Manipulation Architecture for Large Part Manipulation in Industrial Environments

Ibarguren

Daelman

2021

Sensors

View full text Add to dashboard Cite

Collaborative part transportation is an interesting application as many industrial sectors require moving large parts among different areas of the workshops, using a large amount of the workforce on this tasks. Even so, the implementation of such kinds of robotic solutions raises technical challenges like force-based control or robot-to-human feedback. This paper presents a path-driven mobile co-manipulation architecture, proposing an algorithm that deals with all the steps of collaborative part transportation. Starting from the generation of force-based twist commands, continuing with the path management for the definition of safe and collaborative areas, and finishing with the feedback provided to the system users, the proposed approach allows creating collaborative lanes for the conveyance of large components. The implemented solution and performed tests show the suitability of the proposed architecture, allowing the creation of a functional robotic system able to assist operators transporting large parts on workshops.

show abstract

Towards robust human-robot mobile co-manipulation for tasks involving the handling of non-rigid materials using sensor-fused force-torque, and skeleton tracking data

Cited by 18 publications

References 4 publications

Control of Trajectory Tracking for Mobile Manipulator Robot with Kinematic Limitations and Self-Collision Avoidance

Control of Trajectory Tracking for Mobile Manipulator Robot with Kinematic Limitations and Self-Collision Avoidance

Co-manipulation of soft-materials estimating deformation from depth images

Path Driven Dual Arm Mobile Co-Manipulation Architecture for Large Part Manipulation in Industrial Environments

Contact Info

Product

Resources

About