Meta-level Priors for Learning Manipulation Skills with Sparse Features
نویسندگان
چکیده
Manipulation skills need to adapt to the geometric features of the objects that they are manipulating, e.g. the position or length of an action-relevant part of an object. However, only a sparse set of the objects’ features will be relevant for generalizing the manipulation skill between different scenarios and objects. Rather than relying on a human to select the relevant features, our work focuses on incorporating feature selection into the skill learning process. An informative prior over the features’ relevance can guide the robot’s feature selection process. This prior is computed using a meta-level prior, which is learned from previous skills. The meta-level prior is transferred to new skills using meta features. Our robot experiments show that using a meta-level prior results in better generalization performance and more efficient skill learning.
منابع مشابه
Learning Relevant Features for Manipulation Skills using Meta-Level Priors
Robots can generalize manipulation skills between different scenarios by adapting to the features of the objects being manipulated. Selecting the set of relevant features for generalizing skills has usually been performed manually by a human. Alternatively, a robot can learn to select relevant features autonomously. However, feature selection usually requires a large amount of training data, wh...
متن کاملA Monte Carlo-Based Search Strategy for Dimensionality Reduction in Performance Tuning Parameters
Redundant and irrelevant features in high dimensional data increase the complexity in underlying mathematical models. It is necessary to conduct pre-processing steps that search for the most relevant features in order to reduce the dimensionality of the data. This study made use of a meta-heuristic search approach which uses lightweight random simulations to balance between the exploitation of ...
متن کاملSparse Structured Principal Component Analysis and Model Learning for Classification and Quality Detection of Rice Grains
In scientific and commercial fields associated with modern agriculture, the categorization of different rice types and determination of its quality is very important. Various image processing algorithms are applied in recent years to detect different agricultural products. The problem of rice classification and quality detection in this paper is presented based on model learning concepts includ...
متن کاملSparse, complex-valued representations of natural sounds learned with phase and amplitude continuity priors
Complex-valued sparse coding is a data representation which employs a dictionary of two-dimensional subspaces, while imposing sparse, factorial prior on complex amplitudes. When trained on a dataset of natural image patches, it learns phase invariant features which closely resemble receptive fields of complex cells in the visual cortex. Features trained on natural sounds however, rarely reveal ...
متن کاملSim-to-Real Robot Learning from Pixels with Progressive Nets
Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to achieve performance on a real robot, but their potential has been demonstrated in simulated environments. We propose using progressive networks to bridge the reality gap and transfer learned policies from simulation to t...
متن کامل