A Brief Survey on the Role of Dimensionality Reduction in Manipulation Learning and Control

Ficuciello, Fanny; Falco, Pietro; Calinon, Sylvain

doi:10.1109/lra.2018.2818933

Cited by 13 publications

(9 citation statements)

References 92 publications

(109 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Postural synergies refer to the coordinated ways humans control dozens of muscles for different hand postures and these principles affect the design of the anthropomorphic hand. A survey of the techniques for dimensionality reduction as well as learning and control strategies built on subspaces of reduced dimension across different fully actuated and underactuated anthropomorphic designs is contained by Ficuciello et al (2018).…”

Section: Active Exploration: Use Casesmentioning

confidence: 99%

Active Haptic Perception in Robots: A Review

et al. 2019

View full text Add to dashboard Cite

In the past few years a new scenario for robot-based applications has emerged. Service and mobile robots have opened new market niches. Also, new frameworks for shop-floor robot applications have been developed. In all these contexts, robots are requested to perform tasks within open-ended conditions, possibly dynamically varying. These new requirements ask also for a change of paradigm in the design of robots: on-line and safe feedback motion control becomes the core of modern robot systems. Future robots will learn autonomously, interact safely and possess qualities like self-maintenance. Attaining these features would have been relatively easy if a complete model of the environment was available, and if the robot actuators could execute motion commands perfectly relative to this model. Unfortunately, a complete world model is not available and robots have to plan and execute the tasks in the presence of environmental uncertainties which makes sensing an important component of new generation robots. For this reason, today's new generation robots are equipped with more and more sensing components, and consequently they are ready to actively deal with the high complexity of the real world. Complex sensorimotor tasks such as exploration require coordination between the motor system and the sensory feedback. For robot control purposes, sensory feedback should be adequately organized in terms of relevant features and the associated data representation. In this paper, we propose an overall functional picture linking sensing to action in closed-loop sensorimotor control of robots for touch (hands, fingers). Basic qualities of haptic perception in humans inspire the models and categories comprising the proposed classification. The objective is to provide a reasoned, principled perspective on the connections between different taxonomies used in the Robotics and human haptic literature. The specific case of active exploration is chosen to ground interesting use cases. Two reasons motivate this choice. First, in the literature on haptics, exploration has been treated only to a limited extent compared to grasping and manipulation. Second, exploration involves specific robot behaviors that exploit distributed and heterogeneous sensory data.

show abstract

Section: Active Exploration: Use Casesmentioning

confidence: 99%

Active Haptic Perception in Robots: A Review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Multicollinear datasets can lead to overfitting in regression models, which can in turn fail to identify the correct motion intended by the user and produce unusable HRIs. Several solutions have been proposed to solve this problem, including dimensionality reduction and regularization methods 34,35 . Some research works employ dimensionality reduction as the main processing step to implement BoMIs: by compressing the most relevant motion features, the user's motion and the device's inputs are paired 11,12,36,37 .…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Personalization of Body-Machine Interfaces to Control Diverse Robot Types

Macchini

Schiano

Floreano

2021

Preprint

View full text Add to dashboard Cite

Body-Machine Interfaces (BoMIs) for robotic teleoperation can improve a user’s experience and performance. However, the implementation of such systems needs to be optimized on each robot independently, as a general approach has not been proposed to date. Here, we present a novel machine learning method to generate personalized BoMIs from an operator’s spontaneous body movements. The method captures individual motor synergies that can be used for the teleoperation of robots. The proposed algorithm applies to people with diverse behavioral patterns to control robots with diverse morphologies and degrees of freedom, such as a fixed-wing drone, a quadrotor, and a robotic manipulator.

show abstract

“…Interestingly, the compressed representation of actions, in the so-called latent space, preserves the significant properties of the actions' spatial trajectories and facilitates mapping between an observed human action and the reproduced robotic one. 7,8 Accordingly, it allows robots to learn human-like behavioral acts by observing human demonstrators, based on a compact association of the two acting worlds, the observed and the reproduced one.…”

Section: Introductionmentioning

confidence: 99%

“…where, β:Kernel's parameter and μ, n: parameters of the gradient descent process (stps [5][6][7][8][9][10] and…”

mentioning

confidence: 99%

Speed Adaptation in Learning from Demonstration through Latent Space Formulation

2019

View full text Add to dashboard Cite

SUMMARYPerforming actions in a timely manner is an indispensable aspect in everyday human activities. Accordingly, it has to be present in robotic systems if they are going to seamlessly interact with humans. The current work addresses the problem of learning both the spatial and temporal characteristics of human motions from observation. We formulate learning as a mapping between two worlds (the observed and the action ones). This mapping is realized via an abstract intermediate representation termed “Latent Space.” Learned actions can be subsequently invoked in the context of more complex human–robot interaction (HRI) scenarios. Unlike previous learning from demonstration (LfD) methods that cope only with the spatial features of an action, the formulated scheme effectively encompasses spatial and temporal aspects. Learned actions are reproduced under the high-level control of a time-informed task planner. During the implementation of the studied scenarios, temporal and physical constraints may impose speed adaptations in the reproduced actions. The employed latent space representation readily supports such variations, giving rise to novel actions in the temporal domain. Experimental results demonstrate the effectiveness of the proposed scheme in the implementation of HRI scenarios. Finally, a set of well-defined evaluation metrics are introduced to assess the validity of the proposed approach considering the temporal and spatial consistency of the reproduced behaviors.

show abstract

A Brief Survey on the Role of Dimensionality Reduction in Manipulation Learning and Control

Cited by 13 publications

References 92 publications

Active Haptic Perception in Robots: A Review

Active Haptic Perception in Robots: A Review

Data-Driven Personalization of Body-Machine Interfaces to Control Diverse Robot Types

Speed Adaptation in Learning from Demonstration through Latent Space Formulation

Contact Info

Product

Resources

About