Generalized Cylinders for Learning, Reproduction, Generalization, and Refinement of Robot Skills

Ahmadzadeh, S. Reza; Rana, Muhammad Asif; Chernova, Sonia

doi:10.15607/rss.2017.xiii.021

Cited by 10 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their work was aimed towards free space motion and included the whole variance of demonstrations, whereas we look at the variance of motion outside a specified desired direction in an in-contact task. Ahmadzadeh et al (2017) proposed an LfD encoding method which can generate unseen trajectories within the cylinder of the given demonstrations. However, both of these methods are presented as tools for free space motion and not for in-contact tasks.…”

Section: Related Workmentioning

confidence: 99%

Imitation learning-based framework for learning 6-D linear compliant motions

2021

View full text Add to dashboard Cite

We present a novel method for learning from demonstration 6-D tasks that can be modeled as a sequence of linear motions and compliances. The focus of this paper is the learning of a single linear primitive, many of which can be sequenced to perform more complex tasks. The presented method learns from demonstrations how to take advantage of mechanical gradients in in-contact tasks, such as assembly, both for translations and rotations, without any prior information. The method assumes there exists a desired linear direction in 6-D which, if followed by the manipulator, leads the robot’s end-effector to the goal area shown in the demonstration, either in free space or by leveraging contact through compliance. First, demonstrations are gathered where the teacher explicitly shows the robot how the mechanical gradients can be used as guidance towards the goal. From the demonstrations, a set of directions is computed which would result in the observed motion at each timestep during a demonstration of a single primitive. By observing which direction is included in all these sets, we find a single desired direction which can reproduce the demonstrated motion. Finding the number of compliant axes and their directions in both rotation and translation is based on the assumption that in the presence of a desired direction of motion, all other observed motion is caused by the contact force of the environment, signalling the need for compliance. We evaluate the method on a KUKA LWR4+ robot with test setups imitating typical tasks where a human would use compliance to cope with positional uncertainty. Results show that the method can successfully learn and reproduce compliant motions by taking advantage of the geometry of the task, therefore reducing the need for localization accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Imitation learning-based framework for learning 6-D linear compliant motions

2021

View full text Add to dashboard Cite

show abstract

“…In all the experiments, we used the position constraints in (12) to enforce both initial and end point constraints uniformly across all the methods being compared. Further, we uniformly set the number of Gaussian basis functions to five across all the coordinates and all the experiments.…”

Section: Experimental Evaluationmentioning

confidence: 99%

“…Existing work in trajectory-based LfD has contributed a wide range of mathematical representations that encode skills from human demonstrations and then reproduce the learned skills at runtime. Proposed representations include Spring-damper systems with forcing functions [3], Gaussian Mixture Models (GMMs) [4]- [6], Neural Networks (NNs) [7], [8], Gaussian Processes (GPs) [9]- [11], and geometric objects [12], among others. Each of these representations is used to encode the demonstrations in a predefined space or coordinate system (e.g., Cartesian coordinates).…”

Section: Introductionmentioning

confidence: 99%

Skill Acquisition via Automated Multi-Coordinate Cost Balancing

Ravichandar

Ahmadzadeh

Rana

et al. 2019

2019 International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

We propose a learning framework, named Multi-Coordinate Cost Balancing (MCCB), to address the problem of acquiring point-to-point movement skills from demonstrations. MCCB encodes demonstrations simultaneously in multiple differential coordinates that specify local geometric properties. MCCB generates reproductions by solving a convex optimization problem with a multi-coordinate cost function and linear constraints on the reproductions, such as initial, target, and via points. Further, since the relative importance of each coordinate system in the cost function might be unknown for a given skill, MCCB learns optimal weighting factors that balance the cost function. We demonstrate the effectiveness of MCCB via detailed experiments conducted on one handwriting dataset and three complex skill datasets.

show abstract

“…However, their work was aimed towards free space motion and included the whole variance of demonstrations, whereas we look at the variance of motion outside a specified desired direction in an in-contact task. Ahmadzedah et al [17] proposed an LfD encoding method which can generate unseen trajectories within the cylinder of the given demonstrations. However, both of these methods are presented as tools for free space motion and not for incontact tasks.…”

Section: Related Workmentioning

confidence: 99%

Learning compliant assembly motions from demonstration

Suomalainen

Kyrki

2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

We present a novel method for learning 6-D compliant motions from demonstration. The key advantage of our learning method compared to current Learning from Demonstration (LfD) methods is that we learn to take advantage of existing mechanical gradients (such as chamfers) with compliance to perform in-contact motions consisting of both translation and rotation, as in aligning workpieces or attaching hose couplers. We find the desired direction, which leads the robot's end-effector to the location shown in the demonstration either in free space or in contact, separately for translational and rotational motions. The key idea is to first compute a set of directions which would result in the observed motion at each timestep during a demonstration. By taking an intersection over all such sets from a demonstration we find a single desired direction which can reproduce the demonstrated motion. Finding the number of compliant axes and their directions in both rotation and translation is based on the assumption that in the presence of a desired direction of motion, all other observed motion is caused by the contact force of the environment, signalling the need for compliance. We evaluate the method on a KUKA LWR4+ robot with test setups imitating typical tasks where a human would use compliance to cope with positional uncertainty. Results show that the method can successfully learn and reproduce compliant motions by taking advantage of the geometry of the task, therefore reducing the need for initial accuracy. * This work was supported by Academy of Finland, decision 286580. † M. Suomalainen and V. Kyrki are with

show abstract

Generalized Cylinders for Learning, Reproduction, Generalization, and Refinement of Robot Skills

Cited by 10 publications

References 24 publications

Imitation learning-based framework for learning 6-D linear compliant motions

Imitation learning-based framework for learning 6-D linear compliant motions

Skill Acquisition via Automated Multi-Coordinate Cost Balancing

Learning compliant assembly motions from demonstration

Contact Info

Product

Resources

About