Sökresultat

Machine learning methods have a groundbreaking impact in many application domains, but their application on real robotic platforms is still limited. Despite the many challenges associated with combining machine learning technology with robotics, robot learning remains one of the most promising directions for enhancing the capabilities of robots. When deploying learning-based approaches on real rob

Recent methods for imitation learning directly learn a Q-function using an implicit reward formulation rather than an explicit reward function.However, these methods generally require implicit reward regularization to improve stability and often mistreat absorbing states.Previous works show that a squared norm regularization on the implicit reward function is effective, but do not provide a theore

Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a ro

Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or non-differentiable policies. Furthermore, these approaches are particularly relevant where exploration at the action level could cause actuator damage or other safety issues. H

Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting

Learning robot motions from demonstration requires models able to specify vector fields for the full robot pose when the task is defined in operational space. Recent advances in reactive motion generation have shown that learning adaptive, reactive, smooth, and stable vector fields is possible. However, these approaches define vector fields on a flat Euclidean manifold, while representing vector f

Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all. Similarly, if the agent receives also rewards that create suboptimal modes of the objective function, it will likely prematurely stop exploring. More

Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When deploying RL to the real world, several concerns regarding the use of a 'black-box' policy might be raised. In order to make the learned policies more transparent, we

Enligt lagen om anställningsskydd krävs det saklig grund för uppsägning. Saklig grund kan utgöra antingen personliga skäl eller arbetsbrist. Den här uppsatsen kommer främst att behandla fingerad arbetsbrist. Man talar om fingerad arbetsbrist när en arbetsgivare påstår att verksamhetsrelaterade skäl utgjort grunden för uppsägningen när de egentliga grunderna är hänförliga till arbetstagaren personl

China’s opening of reform in 1979 started the transition to a social market economy in 1992 and its accession to the WTO in 2001 are seen are pivotal moments in China’s recent history when assessing its economic growth and investment climate in the last 30 + years. Some theorists (Kokko 1994; Cave 1974) propose the positive spillover effects of FDI however its merits have been called into question

The use of natural gas is increasing globally. At the same time, the cheap and easily accessible resources are decreasing rapidly. Among other alternative gases, biogas is considered since it is a renewable resource. In order for biogas to really become a large scale alternative, it needs to be fully compatible with today’s infrastructure and gas applications. This report is evaluating the technic

A SIFO-survey ordered by E.ON has shown that more than every fourth person in Sweden feels that they have poor knowledge and control over their energy use, and that four out of ten would like to be more aware and to have better control over it. A solution is to provide the householders with feedback of their energy consumption. Studies have shown that householders can reduce energy consumption wit

Title Geothermal Energy Solution at IKEA in Malmö Visualization and monitoring of geothermal energy at IKEA in Malmo concerning 2009-2011 Author Magdalena Horn Environmental Engineering towards Energy Systems Analysis, Lund University Tutors Dr Patrick Lauenburg, Department of Energy Lund University - Lund Institute of Technology Anna Ekdahl, Sweco Environment Tobias Malmgren, IKEA Properties Prob

A concept for a bee, - and beekeeper friendly horizontal top bar beehive for northern climates, aiming to provide a platform for discussion and further development of bee keeping methods. An ergonomic alternative to the heavy handled traditionally used vertical hives, Apivaria aims to offer an older generation a possibility to postpone retirement from beekeeping, while introducing a new generation

A prosperous garden is closely connected to our natural origin and can offer sound activities for most people. To be outside, in green environments is healty both from a psychological and a physical perspective. Most gardens require continous maintenance which can form an appreciated base for routines. When people are getting older and no longer are working, an active and meaningful life can be im

Crowdsourcing is a relatively new technique which aims to make a specific group of people contribute solutions to simple tasks or problems that are published online by some organization. For this they get some reward, which is usually economic in nature. This technique can be embraced by any kind of company, and since it is done online, it can turn out to be a bit problematic, especially when it c

In present world economy the advancement in the communication and globalization have made the physical proximity between two countries, a thing of past. In the present era, developed countries are forging trading treaties with rest of the world to be able to sustain a certain economic growth. This paper investigates the effect of one of these treaties on the Canadian employment at industry level,