Variational Autoencoder Inspired by Brain’s Convergence–Divergence Zones for Autonomous Driving Application

2019 ◽  
pp. 367-377
Author(s):  
Alice Plebe ◽  
Mauro Da Lio
Keyword(s):  
Autonomous Driving ◽  
Variational Autoencoder

scholarly journals Improving Variational Autoencoder based Out-of-Distribution Detection for Embedded Real-time Applications

2021 ◽  
Vol 20 (5s) ◽  
pp. 1-26
Author(s):  
Yeli Feng ◽  
Daniel Jun Xian Ng ◽  
Arvind Easwaran
Keyword(s):  
Machine Learning ◽  
Real Time ◽  
State Of The Art ◽  
Autonomous Driving ◽  
The State ◽  
Theory And Practice ◽  
Data Sets ◽  
Variational Autoencoder ◽  
Distribution Shifts ◽  
Better Than

Uncertainties in machine learning are a significant roadblock for its application in safety-critical cyber-physical systems (CPS). One source of uncertainty arises from distribution shifts in the input data between training and test scenarios. Detecting such distribution shifts in real-time is an emerging approach to address the challenge. The high dimensional input space in CPS applications involving imaging adds extra difficulty to the task. Generative learning models are widely adopted for the task, namely out-of-distribution (OoD) detection. To improve the state-of-the-art, we studied existing proposals from both machine learning and CPS fields. In the latter, safety monitoring in real-time for autonomous driving agents has been a focus. Exploiting the spatiotemporal correlation of motion in videos, we can robustly detect hazardous motion around autonomous driving agents. Inspired by the latest advances in the Variational Autoencoder (VAE) theory and practice, we tapped into the prior knowledge in data to further boost OoD detection’s robustness. Comparison studies over nuScenes and Synthia data sets show our methods significantly improve detection capabilities of OoD factors unique to driving scenarios, 42% better than state-of-the-art approaches. Our model also generalized near-perfectly, 97% better than the state-of-the-art across the real-world and simulation driving data sets experimented. Finally, we customized one proposed method into a twin-encoder model that can be deployed to resource limited embedded devices for real-time OoD detection. Its execution time was reduced over four times in low-precision 8-bit integer inference, while detection capability is comparable to its corresponding floating-point model.

A Lightweight and Multi-OS Compatible Middleware Designed for Autonomous Driving

CICTP 2020 ◽  
2020 ◽  
Author(s):  
Kun Jiang ◽  
Yunlong Wang ◽  
Shengjie Kou ◽  
Diange Yang
Keyword(s):  
Autonomous Driving

Trend of an Autonomous Driving Control Vehicle

2013 ◽  
Vol 133 (9) ◽  
pp. 595-598
Author(s):  
Kenji SUZUKI ◽  
Hisaaki ISHIDA ◽  
Hirofumi INOSE ◽  
Rui KOBAYASHI
Keyword(s):  
Autonomous Driving

Imaging through Scattering Media with a Learning Based Prior

2020 ◽  
Vol 2020 (14) ◽  
pp. 306-1-306-6
Author(s):  
Florian Schiffers ◽  
Lionel Fiske ◽  
Pablo Ruiz ◽  
Aggelos K. Katsaggelos ◽  
Oliver Cossairt
Keyword(s):  
Optimization Problem ◽  
Autonomous Driving ◽  
Scattering Media ◽  
Photon Scattering ◽  
Point Spread ◽  
Spread Function ◽  
Radiative Transport Equation ◽  
Spatio Temporal ◽  
Transient Imaging

Imaging through scattering media finds applications in diverse fields from biomedicine to autonomous driving. However, interpreting the resulting images is difficult due to blur caused by the scattering of photons within the medium. Transient information, captured with fast temporal sensors, can be used to significantly improve the quality of images acquired in scattering conditions. Photon scattering, within a highly scattering media, is well modeled by the diffusion approximation of the Radiative Transport Equation (RTE). Its solution is easily derived which can be interpreted as a Spatio-Temporal Point Spread Function (STPSF). In this paper, we first discuss the properties of the ST-PSF and subsequently use this knowledge to simulate transient imaging through highly scattering media. We then propose a framework to invert the forward model, which assumes Poisson noise, to recover a noise-free, unblurred image by solving an optimization problem.

F1_Tenth_Course_Report_Group_C

2018 ◽  
Author(s):  
Yi Chen ◽  
Sagar Manglani ◽  
Roberto Merco ◽  
Drew Bolduc
Keyword(s):  
Operating System ◽  
Autonomous Driving ◽  
Software Tools ◽  
Simulation Environment ◽  
Robot Operating System ◽  
Available Information

In this paper, we discuss several of major robot/vehicle platforms available and demonstrate the implementation of autonomous techniques on one such platform, the F1/10. Robot Operating System was chosen for its existing collection of software tools, libraries, and simulation environment. We build on the available information for the F1/10 vehicle and illustrate key tools that will help achieve properly functioning hardware. We provide methods to build algorithms and give examples of deploying these algorithms to complete autonomous driving tasks and build 2D maps using SLAM. Finally, we discuss the results of our findings and how they can be improved.

Sign in / Sign up

Export Citation Format

Share Document