Human-aware motion reshaping using dynamical systems

Saveriano, Matteo; Hirt, Fabian; Lee, Dongheui

doi:10.1016/j.patrec.2017.04.014

Cited by 22 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, DMP guarantee convergence towards the target from any initial position. Third, stable dynamical systems are robust to changes in the target position and can be eventually combined with reactive collision avoidance strategies to generate converging and collision-free paths (Saveriano et al 2017).…”

Section: Learning Motion Primitivesmentioning

confidence: 99%

Kinesthetic teaching and attentional supervision of structured tasks in human–robot interaction

Caccavale¹,

Saveriano

Finzi³

et al. 2018

Auton Robot

Self Cite

View full text Add to dashboard Cite

We present a framework that allows a robot manipulator to learn how to execute structured tasks from human demonstrations. The proposed system combines physical human-robot interaction with attentional supervision in order to support kinesthetic teaching, incremental learning, and cooperative execution of hierarchically structured tasks. In the proposed framework, the human demonstration is automatically segmented into basic movements, which are related to a task structure by an attentional system that supervises the overall interaction. The attentional system permits to track the human demonstration at different levels of abstraction and supports implicit non-verbal communication both during the teaching and the execution phase. Attention manipulation mechanisms (e.g. object and verbal cueing) can be exploited by the teacher to facilitate the learning process. On the other hand, the attentional system permits flexible and cooperative task execution. The paper describes the overall system architecture and details how cooperative tasks are learned and executed. The proposed approach is evaluated in a human-robot co-working scenario, showing that the robot is effectively able to rapidly learn and flexibly execute structured tasks.

show abstract

Section: Learning Motion Primitivesmentioning

confidence: 99%

Kinesthetic teaching and attentional supervision of structured tasks in human–robot interaction

Caccavale¹,

Saveriano

Finzi³

et al. 2018

Auton Robot

Self Cite

View full text Add to dashboard Cite

show abstract

“…Segmented pose trajectories are compactly represented as stable dynamical systems, the socalled Dynamic Movement Primitives (DMP) [19], which are used to generate the on-line motion. Dynamical systems are effective in motion generation due to their convergence properties and to their robustness to external perturbations like unforeseen obstacles [20]- [22]. During the demonstration, the RM assigns a unique label to each segment (the symbolic actions a1 to a4 in Fig.…”

Section: Motion Primitives Segmentation and Learningmentioning

confidence: 99%

Symbolic Task Compression in Structured Task Learning

Saveriano¹,

Seegerer²,

Caccavale³

et al. 2019

2019 Third IEEE International Conference on Robotic Computing (IRC)

Self Cite

View full text Add to dashboard Cite

Learning everyday tasks from human demonstrations requires unsupervised segmentation of seamless demonstrations, which may result in highly fragmented and widely spread symbolic representations. Since the time needed to plan the task depends on the amount of possible behaviors, it is preferable to keep the number of behaviors as low as possible. In this work, we present an approach to simplify the symbolic representation of a learned task which leads to a reduction of the number of possible behaviors. The simplification is achieved by merging sequential behaviors, i.e. behaviors which are logically sequential and act on the same object. Assuming that the task at hand is encoded in a rooted tree, the approach traverses the tree searching for sequential nodes (behaviors) to merge. Using simple rules to assign pre-and post-conditions to each node, our approach significantly reduces the number of nodes, while keeping unaltered the task flexibility and avoiding perceptual aliasing. Experiments on automatically generated and learned tasks show a significant reduction of the planning time.

show abstract

“…A DS generates goal-oriented, converging trajectories that connect any two points in the robot's workspace. DS trajectories are generated at runtime, allowing for online motion replanning to handle unexpected perturbations [5][6][7][8]. A stable dynamical system can be learned from human demonstrations [9] in an incremental way [10,11].…”

Section: Introductionmentioning

confidence: 99%

Combining decision making and dynamical systems for monitoring and executing manipulation tasks

Saveriano

Piater

2020

Elektrotech. Inftech.

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a unified framework for online task scheduling, monitoring, and execution that integrates reconfigurable behavior trees, a decision-making framework with integrated low-level control functionalities, and reactive motion generation with stable dynamical systems. In this way, we realize a flexible and reactive system capable of coping with unexpected variations in the executive context without penalizing modularity, expressiveness, and readability of humans. The framework is evaluated in a simulated sorting task showing promising results in terms of flexibility regarding task scheduling and robustness to external disturbances.

show abstract

Human-aware motion reshaping using dynamical systems

Cited by 22 publications

References 25 publications

Kinesthetic teaching and attentional supervision of structured tasks in human–robot interaction

Kinesthetic teaching and attentional supervision of structured tasks in human–robot interaction

Symbolic Task Compression in Structured Task Learning

Combining decision making and dynamical systems for monitoring and executing manipulation tasks

Contact Info

Product

Resources

About