A Survey of Demonstration Learning

Correia, André; Alexandre, Luı́s A.

doi:10.48550/arxiv.2303.11191

Cited by 3 publications

(3 citation statements)

References 151 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Learning From Demonstration (LfD) is another approach that complements sensorimotor control, affordances and RL. LfD enhances robot capabilities by capturing human demonstrations, extracting relevant features and behavior information to establish a connection between object features and the affordance relation, and subsequently replicating it in the robot [24,25]. LfD enables agents to learn from experts, leveraging their insights into desired behaviors and actions.…”

Section: Introductionmentioning

confidence: 99%

Exploring Saliency for Learning Sensory-Motor Contingencies in Loco-Manipulation Tasks

Stefanini,

Lentini,

Grioli

et al. 2024

Robotics

View full text Add to dashboard Cite

The objective of this paper is to propose a framework for a robot to learn multiple Sensory-Motor Contingencies from human demonstrations and reproduce them. Sensory-Motor Contingencies are a concept that describes intelligent behavior of animals and humans in relation to their environment. They have been used to design control and planning algorithms for robots capable of interacting and adapting autonomously. However, enabling a robot to autonomously develop Sensory-Motor Contingencies is challenging due to the complexity of action and perception signals. This framework leverages tools from Learning from Demonstrations to have the robot memorize various sensory phases and corresponding motor actions through an attention mechanism. This generates a metric in the perception space, used by the robot to determine which sensory-motor memory is contingent to the current context. The robot generalizes the memorized actions to adapt them to the present perception. This process creates a discrete lattice of continuous Sensory-Motor Contingencies that can control a robot in loco-manipulation tasks. Experiments on a 7-dof collaborative robotic arm with a gripper, and on a mobile manipulator demonstrate the functionality and versatility of the framework.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring Saliency for Learning Sensory-Motor Contingencies in Loco-Manipulation Tasks

Stefanini,

Lentini,

Grioli

et al. 2024

Robotics

View full text Add to dashboard Cite

show abstract

“…As an active area of research in robotics, LfD has been the subject of significant progress in recent years [ 14 , 15 ]. LfD has also been referred to as imitation learning, programming by demonstration (PbD), and apprenticeship learning (AL) in the literature [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Nonprehensile Manipulation for Rapid Object Spinning via Multisensory Learning from Demonstration

Shin,

Jeon

2024

Sensors

View full text Add to dashboard Cite

Dexterous manipulation concerns the control of a robot hand to manipulate an object in a desired manner. While classical dexterous manipulation strategies are based on stable grasping (or force closure), many human-like manipulation tasks do not maintain grasp stability and often utilize the dynamics of the object rather than the closed form of kinematic relation between the object and the robotic hand. Such manipulation strategies are referred as nonprehensile or dynamic dexterous manipulation in the literature. Nonprehensile manipulation often involves fast and agile movements such as throwing and flipping. Due to the complexity of such motions and uncertainties associated with them, it has been challenging to realize nonprehensile manipulation tasks in a reliable way. In this paper, we propose a new control strategy to realize practical nonprehensile manipulation. First, we make explicit use of multiple modalities of sensory data for the design of control law. Specifically, force data are employed for feedforward control, while position data are used for feedback control. Secondly, control signals (both feedback and feedforward) are obtained through multisensory learning from demonstration (LfD) experiments designed and performed for specific nonprehensile manipulation tasks of concern. To prove the concept of the proposed control strategy, experimental tests were conducted for a dynamic spinning task using a sensory-rich, two-finger robotic hand. The control performance (i.e., the speed and accuracy of the spinning task) was also compared with that of classical dexterous manipulation based on force closure and finger gaiting.

show abstract

“…Correia and Alexandre [11] provide a comprehensive survey of station learning, a paradigm in which agents learn tasks by imitating the expert behavior shown in demonstrations. The survey covers various aspects, including the creation of demonstration datasets, learning methods from demonstrations, optimization techniques, existing benchmarks, and applications of demonstration learning.…”

Section: Introductionmentioning

confidence: 99%

Design and Programming of a Robotic Puppetry Robot Based on Natural Learner Unit Pattern Generators Neural Networks

Shahbazi,

khodabandeh,

Amirkhani

2024

Preprint

View full text Add to dashboard Cite

The purpose of this study is to design and construct a novel interactive game. This game is a robotic learning and imitation task. It is based on visual interaction of the player. The cornerstone technique used in this game is Natural Learner Unit Pattern Generator Neural Networks(NLUPGNN), which is able to generate required motion trajectories based on imitation learning. The systematic design of these neural networks is the main problem solved in this paper. The unit pattern generators can be divided into two subsystems, a rhythmic system and the a discrete system. A special learning algorithm is designed to use these unit pattern generators. The Unit Pattern Generators are connected and coupled to each other to form a network and their unknown parameters are found by a natural policy gradient learning algorithm. The motion sequences train some nonlinear oscillators, then they reproduce motions for a humanoid robot. As a result, the joints of the humanoid body imitate the movements of the teacher in real time. The main contribution of this work is the development of this learning algorithm, which is able to search the weights and topology of the network simultaneously. The algorithm synchronizes the learning steps by coupling the neurons in the last step.

show abstract

A Survey of Demonstration Learning

Cited by 3 publications

References 151 publications

Exploring Saliency for Learning Sensory-Motor Contingencies in Loco-Manipulation Tasks

Exploring Saliency for Learning Sensory-Motor Contingencies in Loco-Manipulation Tasks

Nonprehensile Manipulation for Rapid Object Spinning via Multisensory Learning from Demonstration

Design and Programming of a Robotic Puppetry Robot Based on Natural Learner Unit Pattern Generators Neural Networks

Contact Info

Product

Resources

About