• Corpus ID: 212633851

A machine learning environment for evaluating autonomous driving software

@article{Hanhirova2020AML,
  title={A machine learning environment for evaluating autonomous driving software},
  author={Jussi Hanhirova and Anton Debner and Matias Hyypp{\"a} and Vesa Hirvisalo},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.03576}
}
Autonomous vehicles need safe development and testing environments. Many traffic scenarios are such that they cannot be tested in the real world. We see hybrid photorealistic simulation as a viable tool for developing AI (artificial intelligence) software for autonomous driving. We present a machine learning environment for detecting autonomous vehicle corner case behavior. Our environment is based on connecting the CARLA simulation software to TensorFlow machine learning framework and custom… 

Scalability of a Machine Learning Environment for Autonomous Driving Research

TLDR
This paper presents how scaling of the environment to multiple distributed nodes affects its performance and studies scalability of machine learning environments in the context of mixed collaborative driving.

CarFree: Hassle-Free Object Detection Dataset Generation Using Carla Autonomous Driving Simulator

TLDR
This study presents an open-source automatic GT generation tool, CarFree, based on the Carla autonomous driving simulator, which aims to democratize the daunting task of object detection dataset generation, which was only possible by big companies or institutes due to its high cost.

AI Accelerator Latencies in Hybrid Vehicular Simulation

TLDR
This paper presents the latency behavior with GPU acceleration for CNN processing, which is motivated by using the simulator to find the corner cases that are demanding for the accelerated CNN processing.

Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety

Sebastian Houben1, Stephanie Abrecht2, Maram Akila1, Andreas Bär15, Felix Brockherde10, Patrick Feifel8, Tim Fingscheidt15, Sujan Sai Gannamaneni1, Seyed Eghbal Ghobadi8, Ahmed Hammam8, Anselm

References

SHOWING 1-10 OF 15 REFERENCES

An hybrid simulation tool for autonomous cars in very high traffic scenarios

  • M. GarzónA. Spalanzani
  • Computer Science
    2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV)
  • 2018
TLDR
An open source tool for simulating autonomous vehicles in complex, high traffic, scenarios, which fully integrates and synchronizes two well known simulators: a microscopic, multi-modal traffic simulator and a complex 3D simulator.

CARLA: An Open Urban Driving Simulator

TLDR
This work introduces CARLA, an open-source simulator for autonomous driving research, and uses it to study the performance of three approaches to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end to-end models trained via reinforcement learning.

End to End Learning for Self-Driving Cars

TLDR
A convolutional neural network is trained to map raw pixels from a single front-facing camera directly to steering commands and it is argued that this will eventually lead to better performance and smaller systems.

Scaling for edge inference of deep neural networks

TLDR
There are increasing gaps between the computational complexity and energy efficiency required for the continued scaling of deep neural networks and the hardware capacity actually available with current CMOS technology scaling, in situations where edge inference is required.

AI Accelerator Latencies in Hybrid Vehicular Simulation

TLDR
This paper presents the latency behavior with GPU acceleration for CNN processing, which is motivated by using the simulator to find the corner cases that are demanding for the accelerated CNN processing.

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

TLDR
This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

Recurrent Ladder Networks

TLDR
The recurrent Ladder is able to handle a wide variety of complex learning tasks that benefit from iterative inference and temporal modeling and shows close-to-optimal results on temporal modeling of video data, competitive results on music modeling, and improved perceptual grouping based on higher order abstractions.

Edge computing technologies for Internet of Things: a primer

Network Slicing and Softwarization: A Survey on Principles, Enabling Technologies, and Solutions

TLDR
The diverse use cases and network requirements of network slicing, the pre-slicing era, considering RAN sharing as well as the end-to-end orchestration and management, encompassing the radio access, transport network and the core network are outlined.

TensorFlow: Large-Scale Machine

  • Learning on Heterogeneous Systems
  • 2015