Grasp planning and most specifically the grasp space exploration is still an open issue in robotics. This article presents a data-driven oriented methodology to model the grasp space of a multi-fingered adaptive gripper for known objects. This method relies on a limited dataset of manually specified expert grasps, and uses variational autoencoder to learn grasp intrinsic features in a compact way from a computational point of view. The learnt model can then be used to generate new non-learnt gripper configurations to explore the grasp space. accepted at SYSID 2021 conference
In this paper we study the question of life long learning of behaviors from human demonstrations by an intelligent system. One approach is to model the observed demonstrations by a stationary policy. Inverse rein-forcement learning, on the other hand, searches a reward function that makes the observed policy closed to optimal in the corresponding Markov decision process. This approach provides a model of the task solved by the demonstrator and has been shown to lead to better generalization in un-known contexts. However both approaches focus on learning a single task from the expert demonstration. In this paper we propose a feature learn-ing approach for inverse reinforcement learning in which several different tasks are demonstrated, but in which each task is modeled as a mixture of several, simpler, primitive tasks. We present an algorithm based on an al-ternate gradient descent to learn simultaneously a dictionary of primitive tasks (in the form of reward functions) and their combination into an ap-proximation of the task underlying observed behavior. We illustrate how this approach enables efficient re-use of knowledge from previous demon-strations. Namely knowledge on tasks that were previously observed by the learner is used to improve the learning of a new composite behavior, thus achieving transfer of knowledge between tasks.
Publication . Part of book or chapter of book . 2019
International audience; It has been 35 years since Igbozurike and Raza (1983), and rural communities in Nigeria continue to face many of the challenges identified in the ARMTI seminar. Poverty and rural-urban migration remain widespread in Nigeria. Further issues of security and terrorism have also made their way into the array of problems facing rural communities in Nigeria. Therefore, the aim of this paper is to review the issues affecting the quality of life in 21st century rural Nigeria, in order to ascertain what has changed or remained the same since 1983. In achieving the study aim, the parameters used by Igbozurike and Raza (1983) will be linked with current literature on the quality of life in rural Nigeria. The paper will look at the following parameters: socioeconomic indicators, social services and infrastructure, nutritional status, population structure and mobility, institutional frameworks and the role of Agricultural Development Projects (ADPs).
Publication . Part of book or chapter of book . 2007
Abstract. MODIS (Moderate Resolution Imaging Spectroradiometer) satellite observations of fire size and ERA-Interim meteorological reanalysis are used to derive a relationship between burnt area and wind speed over the Mediterranean region and Eastern Europe. The largest wildfire size does not show a strong response with respect to wind speed in Eastern Europe. In the Mediterranean, as intuitively expected, the burnt area associated with the largest wildfires is an increasing function of wind speed for moderate temperature anomalies. In situations of severe heatwaves, the relationship between burnt area and wind speed displays a bimodal shape. Burnt areas are large for low 10 m wind speed (lower than 2 m s−1), decrease for moderate wind speed values (lower than 5 m s−1 and larger than 2 m s−1) and increase again for high wind speed (higher than 5 m s−1). To explain such behavior we use a stochastic model of fire propagation, known as a probabilistic cellular automata. This model uses a probabilistic local rule to derive the total burnt area. The observed relationship between burnt area and wind speed can be interpreted in terms of percolation threshold above which the propagation in the model is infinite, which mainly depends on local terrain slope and vegetation state (type, density, fuel moisture). In Eastern Europe, the percolation threshold is never exceeded for observed wind speeds. In the Mediterranean Basin we see two behaviors. During moderately hot weather, the percolation threshold is passed when the wind grows strong. On the other hand, in situations of severe Mediterranean heatwaves, moderate wind speed values impair the propagation of the wildfire against the wind and do not sufficiently accelerate the forward propagation to allow a growth of wildfire size.
You have been invited to join Assessing the socio-economic impact of digitalisation in rural areas Research Community Dashboard as a manager. Fill in the verification code, sent to your email, to accept the invitation request.
We are unable to process the request because the link is invalid, or it has expired.