Generating scenarios with diverse pedestrian behaviors for autonomous vehicle testing

M Priisalu, A Pirinen, C Paduraru… - … on Robot Learning, 2022 - proceedings.mlr.press
There exist several datasets for develo** self-driving car methodologies. Manually
collected datasets impose inherent limitations on the variability of test cases and it is …

Behaviorally diverse traffic simulation via reinforcement learning

S Shiroshita, S Maruyama, D Nishiyama… - 2020 IEEE/RSJ …, 2020 - ieeexplore.ieee.org
Traffic simulators are important tools in autonomous driving development. While continuous
progress has been made to provide developers more options for modeling various traffic …

Anticipatory thinking in design

M Klenk, M Hong, S Hakimi, C Wu - AI Magazine, 2023 - Wiley Online Library
Anticipatory thinking (AT) and design have many commonalities. We identify three
challenges for all computational AT systems: representation, generation, and evaluation. We …

Efficient Generation of Safety-Critical Scenarios Combining Dynamic and Static Scenario Parameters

Z Wang, X Li, D Wei, L Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Due to the rarity of safety-critical scenarios, the safety of autonomous driving decision-
making algorithms cannot be fully guaranteed in open environments, which limits their …

Varied Realistic Autonomous Vehicle Collision Scenario Generation

M Priisalu, C Paduraru, C Smichisescu - Scandinavian Conference on …, 2023 - Springer
Recently there has been an increase in the number of available autonomous vehicle (AV)
models. To evaluate and compare the safety of the various models the AVs need to be …

A Counterfactual Safety Margin Perspective on the Scoring of Autonomous Vehicles' Riskiness

A Zanardi, A Censi, M Atzei, L Di Lillo… - arxiv preprint arxiv …, 2023 - arxiv.org
Autonomous Vehicles (AVs) have the potential to provide numerous societal benefits, such
as decreased road accidents and increased overall transportation efficiency. However …

Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle

M Priisalu - arxiv preprint arxiv:2309.06313, 2023 - arxiv.org
It is difficult to perform 3D reconstruction from on-vehicle gathered video due to the large
forward motion of the vehicle. Even object detection and human sensing models perform …

Multi-Robot System Architecture Focusing on Plan Recovery for Dynamic Environments

CJT da Silva, CG Ralha - 2023 IEEE Symposium Series on …, 2023 - ieeexplore.ieee.org
The complexity of multi-robot systems (MRS) involves the challenging task of robot
coordination to achieve the system's goal. That indicates the necessity to integrate …

Urban Driving Games: Structure, Computation, and Risk

A Zanardi - 2023 - research-collection.ethz.ch
As autonomous technologies burgeon and integrate into our complex, multifaceted world,
the necessity for a systematic and rational methodology for interactions among agents …

Multi-scale Pedestrian Navigation and Movement in Urban Areas

O Thompson Sargoni - 2023 - discovery.ucl.ac.uk
Sustainable transport planning highlights the importance of walking to low-carbon and
healthy urban transport systems. Studies have identified multiple ways in which vehicle …