Search Results for author:
Found 21 papers, 4 papers with code
Affordance Blending Networks
As a theoretical lens, affordances bridge the gap between effect and action, providing a nuanced understanding of the connections between agents' actions on entities and the effect of these actions.
Bidirectional Progressive Neural Networks with Episodic Return Progress for Emergent Task Sequencing and Robotic Skill Transfer
In an attempt to exemplify such a development by inspiring how humans acquire knowledge and transfer skills among tasks, we introduce a novel multi-task reinforcement learning framework named Episodic Return Progress with Bidirectional Progressive Neural Networks (ERP-BPNN).
Conditional Neural Expert Processes for Learning from Demonstration
Furthermore, we compare the performance of CNEP with another LfD framework, namely Conditional Neural Movement Primitives (CNMP), on a range of tasks, including experiments on a real robot.
A Reinforcement Learning Based Controller to Minimize Forces on the Crutches of a Lower-Limb Exoskeleton
Accordingly, we design a model and a learning framework for a human-exoskeleton system with crutches.
Correspondence learning between morphologically different robots via task demonstrations
To be specific, besides robots with similar morphologies with different degrees of freedom, we show that a fixed-based manipulator robot with joint control and a differential drive mobile robot can be addressed within the proposed framework.
Multi-Object Graph Affordance Network: Enabling Goal-Oriented Planning through Compound Object Affordances
Learning object affordances is an effective tool in the field of robot learning.
Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers
We compare the performance of our proposed architecture with state-of-the-art symbol discovery methods in a simulated tabletop environment where the robot needs to discover symbols related to the relative positions of objects to predict the observed effect successfully.
Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning
In contrast to behavior cloning, which assumes the data is collected from expert demonstrations, offline RL can work with non-expert data and multimodal behavior policies.
Meta-World Conditional Neural Processes
To reduce the number of samples required at test time, we first obtain a latent representation of the transition dynamics from a single rollout from the test environment with hidden parameters.
World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges
Therefore, in this paper, we clarify the definitions, relationships, and status of current research on these topics, as well as missing pieces of world models and predictive coding in conjunction with crucially related concepts such as the free-energy principle and active inference in the context of cognitive and developmental robotics.
Learning Social Navigation from Demonstrations with Conditional Neural Processes
Sociability is essential for modern robots to increase their acceptability in human environments.
Predictive Event Segmentation and Representation with Neural Networks: A Self-Supervised Model Assessed by Psychological Experiments
We compared event segmentation behaviors of participants and our model with this video in two hierarchical event segmentation levels.
High-level Features for Resource Economy and Fast Learning in Skill Transfer
To be concrete, in our simulation experiments, we either apply principal component analysis (PCA) or slow feature analysis (SFA) on the signals collected from the last hidden layer of a deep network while it performs a source task, and use these features for skill transfer in a new target task.
Object and Relation Centric Representations for Push Effect Prediction
Our approach enables the robot to predict and adapt the effect of a pushing action as it observes the scene.
DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning
We propose a novel general method that finds action-grounded, discrete object and effect categories and builds probabilistic rules over them for non-trivial action planning.
Reward Conditioned Neural Movement Primitives for Population Based Variational Policy Optimization
For this, the experience of the robot, which can be bootstrapped from demonstrated trajectories, is used to train a novel Neural Processes-based deep network that samples from its latent space and generates the required trajectories given desired rewards.
Time Perception: A Review on Psychological, Computational and Robotic Models
Firstly, we introduce a brief background from the psychology and neuroscience literature, covering the characteristics and models of time perception and related abilities.
ACNMP: Skill Transfer and Task Extrapolation through Learning from Demonstration and Reinforcement Learning via Representation Sharing
To equip robots with dexterous skills, an effective approach is to first transfer the desired skill via Learning from Demonstration (LfD), then let the robot improve it by self-exploration via Reinforcement Learning (RL).
Belief Regulated Dual Propagation Nets for Learning Action Effects on Articulated Multi-Part Objects
In this paper, we introduce Belief Regulated Dual Propagation Networks (BRDPN), a general purpose learnable physics engine, which enables a robot to predict the effects of its actions in scenes containing groups of articulated multi-part objects.
Robotics
Generalization in Transfer Learning
Furthermore, we increase the generalization capacity in widely used transfer learning benchmarks by using maximum entropy regularization, different critic methods, and curriculum learning in an adversarial setup.
Symbol Emergence in Cognitive Developmental Systems: a Survey
However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.
