Filters








10 Hits in 2.7 sec

The AI Driving Olympics at NeurIPS 2018 [article]

Julian Zilly, Jacopo Tani, Breandan Considine, Bhairav Mehta, Andrea F. Daniele, Manfred Diaz, Gianmarco Bernasconi, Claudio Ruch, Jan Hakenberg, Florian Golemo, A. Kirsten Bowser, Matthew R. Walter, Ruslan Hristov (+4 others)
2019 arXiv   pre-print
The first AI-DO, AI-DO 1, occurred at the Neural Information Processing Systems (NeurIPS) conference in December 2018.  ...  To help bridge this gap, we created the 'AI Driving Olympics' (AI-DO), a competition with the objective of evaluating the state of the art in machine learning and artificial intelligence for mobile robotics  ...  Acknowledgements We would like to thank NeurIPS and in particular Sergio Escalera and Ralf Herbrich for giving us the opportunity to share the AI Driving Olympics with the machine learning community.  ... 
arXiv:1903.02503v1 fatcat:udpe2g7ypjckppq65qgmcnb7ru

Bridging Sim2Real Gap Using Image Gradients for the Task of End-to-End Autonomous Driving [article]

Unnikrishnan R Nair, Sarthak Sharma, Udit Singh Parihar, Midhun S Menon, Srikanth Vidapanakal
2022 arXiv   pre-print
The Deepracer challenge is a part of a series of embodied intelligence competitions in the field of autonomous vehicles, called The AI Driving Olympics (AI-DO).  ...  The overall objective of the AI-DO is to provide accessible mechanisms for benchmarking progress in autonomy applied to the task of autonomous driving.  ...  The NeurIPS 2021 AWS DeepRacer challenge is a part of a series of competitions in the area of AV called The AI Driving Olympics (AI-DO).  ... 
arXiv:2205.07481v1 fatcat:l4esvxxyfnfzrgre5kknuujuma

Confucius, Cyberpunk and Mr. Science: Comparing AI ethics between China and the EU [article]

Pascale Fung, Hubert Etienne
2021 arXiv   pre-print
In order to better understand the philosophical roots and cultural context underlying ethical principles in AI, we propose to analyse and compare the ethical principles endorsed by the Chinese National  ...  New Generation Artificial Intelligence Governance Professional Committee (CNNGAIGPC) and those elaborated by the European High-level Expert Group on AI (HLEGAI).  ...  , ICML, IJCAI, NeurIPS, include at least one AI ethics related workshop, tutorial, theme track or topic of interest (See Appendix)  ... 
arXiv:2111.07555v1 fatcat:bbbp2erufjc3xkax3pio7t7qyu

An Embarrassingly Pragmatic Introduction to Vision-based Autonomous Robots [article]

Marcos V. Conde
2021 arXiv   pre-print
We review the state-of-the-art of fundamental problems and demonstrate that many methods employed at small-scale are similar to the ones employed in real Self-driving cars from companies like Tesla or  ...  Developing an AI able to drive a car without human intervention and a small robot to deliver packages in the city may seem like different problems, nevertheless from the point of view of perception and  ...  The ai driving olympics at neurips 2018, 2019. [103] Barret Zoph, Ekin D. Cubuk, Golnaz Ghiasi, Tsung-Yi Lin, Jonathon Shlens, and Quoc V. Le.  ... 
arXiv:2112.05534v2 fatcat:3drhsxelvvdwvpsq5rvfpnukam

Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World

Peter Almasi, Robert Moni, Balint Gyires-Toth
2020 2020 International Joint Conference on Neural Networks (IJCNN)  
The method is evaluated in the Duckietown environment, where the agent has to follow the lane based on a monocular camera input.  ...  The desired approach would be to train the agent in a simulator and transfer it to the real world.  ...  ACKNOWLEDGEMENTS The research presented in this paper has been supported by Continental Automotive Hungary Ltd., by the European Union, co-financed by the European Social Fund (EFOP-3.6.  ... 
doi:10.1109/ijcnn48605.2020.9207497 dblp:conf/ijcnn/AlmasiMG20 fatcat:7fgtjip4vvdozk4zfr23zh4p5m

Robust Reinforcement Learning-based Autonomous Driving Agent for Simulation and Real World [article]

Péter Almási, Róbert Moni, Bálint Gyires-Tóth
2020 arXiv   pre-print
The method is evaluated in the Duckietown environment, where the agent has to follow the lane based on a monocular camera input.  ...  The desired approach would be to train the agent in a simulator and transfer it to the real world.  ...  ACKNOWLEDGEMENTS The research presented in this paper has been supported by Continental Automotive Hungary Ltd., by the European Union, co-financed by the European Social Fund (EFOP-3.6.  ... 
arXiv:2009.11212v1 fatcat:dkbjmr4fujc5lapxngrhua6cny

Towards Better Driver Safety: Empowering Personal Navigation Technologies with Road Safety Awareness [article]

Runsheng Xu, Shibo Zhang, Yue Zhao, Peixi Xiong, Allen Yilun Lin, Brent Hecht, Jiaqi Ma
2021 arXiv   pre-print
To address this problem, this paper aims to begin the process of adding road safety awareness to navigation systems.  ...  Finally, we discuss the factors to consider when extending our road safety classifier to other regions and potential new safety designs enabled by our road safety predictions.  ...  In NeurIPS 2021 AI for Science Workshop.  ... 
arXiv:2006.03196v5 fatcat:gxj2kt3vqfdjroraoa47jeowmm

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022 arXiv   pre-print
As a result, a growing community of researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of risks and opportunities of automated decision-making  ...  Moreover we rigorously identify the three most popular fairness datasets, namely Adult, COMPAS and German Credit, for which we compile in-depth documentation.  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc Behaghel, Asia Biega, Marko Bohanec, Chris  ... 
arXiv:2202.01711v2 fatcat:5hf4a42pubc5vnt7tw3al4m5bq

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022
As a result, a growing community of algorithmic fairness researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of the risks and opportunities  ...  Firstly, we summarize the merits and limitations of popular algorithmic fairness datasets, questioning their suitability as general-purpose fairness benchmarks.  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc  ... 
doi:10.48550/arxiv.2202.01711 fatcat:mav36x3w5namjhurzpevtsmsju

The Gutenberg Dialogue Dataset

Richard Csaky, Gábor Recski
2021 Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   unpublished
We describe our dialogue extraction pipeline, analyze the effects of the various heuristics used, and present an error analysis of extracted dialogues.  ...  Finally, we conduct experiments showing that better response quality can be achieved in zero-shot and finetuning settings by training on our data than on the larger but much noisier Opensubtitles dataset  ...  Work partly supported by Project FIEK 16-1-2016-0007, financed by the FIEK 16 funding scheme of the Hungarian National Research, Development and Innovation Office (NKFIH).  ... 
doi:10.18653/v1/2021.eacl-main.11 fatcat:ebjo4hbaebaqbdeqtuyv4i7zwu