Sökning: "Local Navigation"

Visar resultat 1 - 5 av 53 uppsatser innehållade orden Local Navigation.

1. 1. Uncontrolled intersection coordination of the autonomous vehicle based on multi-agent reinforcement learning.

   Master-uppsats, Malmö universitet/Fakulteten för teknik och samhälle (TS)

   Författare :Isaac Arnold McSey; [2023]
   Nyckelord :Autonomous Vehicles AVs ; Road Safety; Fuel Efficiency; Business Dynamics; Intersections; Human-Driven Vehicles HDVs ; Pedestrians; Multi-Agent Reinforcement Learning MARL ; Multi-Agent Deep Deterministic Policy Gradient MADDPG ; Algorithmic Interactions; Uncontrolled Intersections; Global Insights; Safety Improvements; Comfort Improvements; Learning Process; Global Experiences; Complex Environments; Passenger Comfort; Navigation;

   Sammanfattning : This study explores the application of multi-agent reinforcement learning (MARL) to enhance the decision-making, safety, and passenger comfort of Autonomous Vehicles (AVs)at uncontrolled intersections. The research aims to assess the potential of MARL in modeling multiple agents interacting within a shared environment, reflecting real-world situations where AVs interact with multiple actors. LÄS MER

3. 2. The ecological impact of artificial light at night in landscape architecture : strategies and guidelines for street lights for the benefit of biodiversity and local wildlife

   Kandidat-uppsats, SLU/Dept. of Urban and Rural Development

   Författare :Zozan Altun; [2023]
   Nyckelord :light pollution; artificial light at night; ecology; biodiversity; local wildlife; landscape architecture; guidelines; strategies;

   Sammanfattning : Artificial light at night (ALAN) is an increasingly common form of light pollution that contributes to biodiversity loss, loss of dark habitats, disrupting populations both on an individual- and population level by invading biodiversity hot spots. Recent studies show that artificial light is increasing at a rate of approximately 6% annually over Earth’s surface, and 88% of Europe and 47% of the United States experience light pollution on a nightly basis. LÄS MER

4. 3. Velocity Obstacle method adapted for Dynamic Window Approach

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Florian Coissac; [2023]
   Nyckelord :Autonomous navigation; Local planning; Dynamic obstacle avoidance; ROS; Autonom navigering; Lokal planering; Dynamiskt undvikande av hinder; ROS;

   Sammanfattning : This thesis project is part of an internship at Visual Behavior. The company aims at producing computer vision models for robotics, helping the machine to better understand the world through the camera eye. The image holds many features that deep learning models are able to extract: navigable area, depth inference and object detection. LÄS MER

5. 4. Deep Reinforcement Learning on Social Environment Aware Navigation based on Maps

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Victor Sanchez; [2023]
   Nyckelord :Deep Reinforcement Learning; Environment-aware navigation; Robotics; Artificial Intelligence; Apprentissage par renforcement profond; Navigation consciente de l’humain; Intelligence Artificielle; Robotique; Djup Förstärkande Inlärning; Människomedveten navigering; Robotik; Artificiell Intelligens;

   Sammanfattning : Reinforcement learning (RL) has seen a fast expansion in recent years of its successful application to a range of decision-making and complex control tasks. Moreover, deep learning offers RL the opportunity to enlarge its spectrum of complex fields. LÄS MER

7. 5. Skyline Delineation for Localization in Occluded Environments : Improved Skyline Delineation using Environmental Context from Deep Learning-based Semantic Segmentation

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Kyle William Coble; [2023]
   Nyckelord :Skyline delineation; Skyline detection; Semantic segmentation; Terrain based navigation; Digital elevation models; Uncrewed surface vessel; Planetary exploration robots; Horisont avgränsning; Horisont upptäckt; Semantisk segmentering; Terrängbaserad navigering; Digitala höjdmodeller; Obemannat ytfartyg; Planetariska utforskningsrobotar;

   Sammanfattning : This thesis addresses the problem of improving the delineation of skylines, also referred to as skyline detection, in occluded and challenging environments where existing skyline delineation methods may struggle or fail. Delineated skylines can be used in monocular camera localization methods by comparing delineated skylines to digital elevation model data to estimate a position based on known terrain. LÄS MER