Sökning: "tactical decision-making"

Visar resultat 1 - 5 av 32 avhandlingar innehållade orden tactical decision-making.

1. 1. Safe, human-like, decision-making for autonomous driving

   Författare :Dapeng Liu; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; human-like behaviors.; imitation learning; Autonomous driving; reinforcement learning; decision making; safety;

   Sammanfattning : Autonomous driving technology can significantly improve transportation by saving lives and social costs and increasing traffic efficiency and availability. Decision-making is a critical component of driving ability. Complex traffic environments and interactions between road users bring about many challenges in decision-making. LÄS MER

3. 2. Tactical decision-making for autonomous driving: A reinforcement learning approach

   Författare :Carl-Johan E Hoel; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; genetic algorithm; Monte Carlo tree search; deep reinforcement learning; tactical decision-making; autonomous driving; neural network;

   Sammanfattning : The tactical decision-making task of an autonomous vehicle is challenging, due to the diversity of the environments the vehicle operates in, the uncertainty in the sensor information, and the complex interaction with other road users. This thesis introduces and compares three general approaches, based on reinforcement learning, to creating a tactical decision-making agent. LÄS MER

4. 3. Decision-Making in Autonomous Driving using Reinforcement Learning

   Författare :Carl-Johan E Hoel; Chalmers tekniska högskola; []
   Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Monte Carlo tree search; epistemic uncertainty; tactical decision-making; reinforcement learning; neural networks; aleatoric uncertainty; autonomous driving;

   Sammanfattning : The main topic of this thesis is tactical decision-making for autonomous driving. An autonomous vehicle must be able to handle a diverse set of environments and traffic situations, which makes it hard to manually specify a suitable behavior for every possible scenario. LÄS MER

5. 4. Complexity-aware Decision-making with Applications to Large-scale and Human-in-the-loop Systems

   Författare :Elis Stefansson; Karl H. Johansson; Henrik Sandberg; Iman Shames; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Complexity-aware Decision-making; Automata Theory; Automatic Control; Optimal Control; Kolmogorov Complexity; Hierarchical Finite State Machines; Large-scale Systems; Human-in-the-loop; Game Theory; Human Decision-making; Autonomous vehicles; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis considers control systems governed by autonomous decision-makers and humans. We formalise and compute low-complex control policies with applications to large-scale systems, and propose human interaction models for controllers to compute interaction-aware decisions. LÄS MER

7. 5. Supporting Dynamic Decision Making in Naval Search and Evasion Tasks

   Författare :Christofer Waldenström; Love Ekenberg; Mats Danielson; Peter Thunholm; Neville Stanton; Stockholms universitet; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Decision support; visualization; dynamic decision-making; naval warfare; expanding search area; field of safe travel; search task; evasion task; ecological interface; anti-submarine warfare; constraints; flaming datum; Computer and Systems Sciences; data- och systemvetenskap; Ledningsvetenskap;

   Sammanfattning : This thesis investigates a decision aid to support tasks where there is an initial sighting of an object and then the decision maker has to guide some vehicles, either to reestablish contact with the lost object or to stay clear of it. As such, the tasks are analogous to naval search and evasion tasks. LÄS MER