Adaptive learning based on guided exploration for decision making at roundabouts

F Gritschneder, P Hatzelmann, M Thom… - … Intelligent Vehicles …, 2016 - ieeexplore.ieee.org
… for the purpose of safe behavioral planning in an automotive scenario in this paper. …
Dillmann, “Probabilistic MDPBehavior Planning for Cars,” in IEEE Conference on Intelligent …

Virtual target-based overtaking decision, motion planning, and control of autonomous vehicles

H Chae, K Yi - IEEE Access, 2020 - ieeexplore.ieee.org
… of the vehicle. We propose efficient decision-making and motion planning based on
probabilistic … To improve safety within the near future, probabilistic predictions are employed that …

Human intention-based collision avoidance for autonomous cars

D Osipychev, D Tran, W Sheng… - 2017 American …, 2017 - ieeexplore.ieee.org
… a probability pc2(s). Assuming that vehicles don’t intentionally collide with each other, we
treat these two probabilities as independent so the probability of collision is the following joint …

Modeling pedestrian behavior in pedestrian-vehicle near misses using inverse reinforcement learning algorithms

P Nasernejad - 2021 - open.library.ubc.ca
… between vehicles, which in turn decreased the probability of … in approaching vehicles
speed, the probability of pedestrians … besides vehicle speed, pedestrian distance to the vehicle

MPDM: Multi-policy Decision-Making from Autonomous Driving to Social

AG Cunningham, E Galceran, D Mehta… - Control Strategies for …, 2018 - books.google.com
… We remain in the right lane behind vehicle 1 until vehicle 2 initiates a lane … We pass both
vehicles and return to the right lane, from [1] c … Probabilistic MDP-behavior planning for cars. In: …

Multiagent modeling of pedestrian-vehicle conflicts using Adversarial Inverse Reinforcement Learning

P Nasernejad, T Sayed, R Alsaleh - Transportmetrica A: transport …, 2023 - Taylor & Francis
… modeling of pedestrian and vehicle maneuvers in near misses … the probability of a transition
from state s to state s ′ taking actions ( a 1 , … , a N ). η is a subset of transition probabilities

Dynamic Adjustment of Reward Function for Proximal Policy Optimization with Imitation Learning: Application to Automated Parking Systems

M Albilani, A Bouzeghoub - 2022 IEEE Intelligent Vehicles …, 2022 - ieeexplore.ieee.org
… Moreover, these methods suffer from a non-linearity issue of vehicle dynamics, that causes
… to explore an empty parking spot, plan then park a car in a random parking spot by avoiding …

Reinforcement Learning for Shared Driving

S Ko, R Langari - IFAC-PapersOnLine, 2023 - Elsevier
… is a map from a given state to a probability distribution for each possible action. The agent
… One stopped vehicle is placed in front of the ego-vehicle’s initial position. The other vehicles

Interactive visualization for testing markov decision processes: MDPVIS

S McGregor, H Buckingham, TG Dietterich… - Journal of visual …, 2017 - Elsevier
… Domain experts may have mental models of MDP behavior … in Mountain Car store energy
by rocking the car back and … for Mountain Car with a parameter controlling the probability of …

[PDF][PDF] Automated Lane Change Decision Making in Highway using a Hybrid Approach

O Caldıran, E Baglayici, M Dousti, E Mungan, EE Bulut… - 2021 - scitepress.org
probabilistic assessment of road lanes and a deterministic assessment of the inter-vehicular
gaps. For the probabilistic … Probabilistic MDP-Behavior Planning for Cars. In 2011 IEEE 14th …