scholarly journals Zero-Shot Autonomous Vehicle Policy Transfer: From Simulation to Real-World via Adversarial Learning

2020 ◽  
Author(s):  
Behdad Chalaki ◽  
Logan E. Beaver ◽  
Ben Remer ◽  
Kathy Jang ◽  
Eugene Vinitsky ◽  
...  
Keyword(s):  
Real World ◽  
Autonomous Vehicle ◽  
Policy Transfer ◽  
Adversarial Learning

Generated Trajectory of Extended Lateral Guided Sensor Steering Mechanism for Steered Autonomous Vehicles in Real World Environments

2017 ◽  
Vol 29 (4) ◽  
pp. 660-667 ◽  
Author(s):  
Yoshihiro Takita ◽  
Keyword(s):  
Experimental Data ◽  
Control System ◽  
Real World ◽  
Autonomous Vehicles ◽  
Autonomous Vehicle ◽  
Steering Mechanism ◽  
World Environment

This paper discusses the generated trajectory of an extended lateral guided sensor steering mechanism (SSM) method for a steered autonomous vehicle moving in a real world environment. In a previous study, an extended SSM was applied to the Smart Dump 9 and AR Chair robots for following preset waypoints on a map. These studies showed only the schematic idea of the method; the precise performance of the generated trajectory was not shown. This paper compares the Smart Dump 9 robot with a newly developed AR Skipper robot; these robots participated in the Tsukuba Challenge in 2015 and 2016, respectively. Finally, experimental data from the Tsukuba Challenge 2016 demonstrates the advantages of the extended SSM and developed control system.

Real- World Maneuver Extraction for Autonomous Vehicle Validation: A Comparative Study

2019 ◽  
Author(s):  
Ahmetcan Erdogan ◽  
Burak Ugranli ◽  
Erkan Adali ◽  
Ali Sentas ◽  
Eren Mungan ◽  
...  
Keyword(s):  
Comparative Study ◽  
Real World ◽  
Autonomous Vehicle

Analysis of LiDAR and Camera Data in Real-World Weather Conditions for Autonomous Vehicle Operations

2020 ◽  
Author(s):  
Nick Goberville ◽  
Mohammad El-Yabroudi ◽  
Mark Omwanas ◽  
Johan Rojas ◽  
Rick Meyer ◽  
...  
Keyword(s):  
Real World ◽  
Autonomous Vehicle ◽  
Weather Conditions

scholarly journals Open Category Classification by Adversarial Sample Generation

2017 ◽  
Author(s):  
Yang Yu ◽  
Wei-Yang Qu ◽  
Nan Li ◽  
Zimin Guo
Keyword(s):  
Real World ◽  
Learning Strategy ◽  
Adversarial Learning ◽  
Training Samples ◽  
Classification Tasks

In real-world classification tasks, it is difficult to collect training samples from all possible categories of the environment. Therefore, when an instance of an unseen class appears in the prediction stage, a robust classifier should be able to tell that it is from an unseen class, instead of classifying it to be any known category. In this paper, adopting the idea of adversarial learning, we propose the ASG framework for open-category classification. ASG generates positive and negative samples of seen categories in the unsupervised manner via an adversarial learning strategy. With the generated samples, ASG then learns to tell seen from unseen in the supervised manner. Experiments performed on several datasets show the effectiveness of ASG.

Design and implementation of human driving data–based active lane change control for autonomous vehicles

2020 ◽  
Vol 235 (1) ◽  
pp. 55-77
Author(s):  
Heungseok Chae ◽  
Yonghwan Jeong ◽  
Hojun Lee ◽  
Jongcherl Park ◽  
Kyongsu Yi
Keyword(s):  
Real World ◽  
Autonomous Vehicles ◽  
High Speed ◽  
Control Algorithm ◽  
Autonomous Vehicle ◽  
Autonomous Driving ◽  
Lane Change ◽  
Driving Mode ◽  
Lane Changes ◽  
Safety Indices

This article describes the design, implementation, and evaluation of an active lane change control algorithm for autonomous vehicles with human factor considerations. Lane changes need to be performed considering both driver acceptance and safety with surrounding vehicles. Therefore, autonomous driving systems need to be designed based on an analysis of human driving behavior. In this article, manual driving characteristics are investigated using real-world driving test data. In lane change situations, interactions with surrounding vehicles were mainly investigated. And safety indices were developed with kinematic analysis. A safety indices–based lane change decision and control algorithm has been developed. In order to improve safety, stochastic predictions of both the ego vehicle and surrounding vehicles have been conducted with consideration of sensor noise and model uncertainties. The desired driving mode is decided to cope with all lane changes on highway. To obtain desired reference and constraints, motion planning for lane changes has been designed taking stochastic prediction-based safety indices into account. A stochastic model predictive control with constraints has been adopted to determine vehicle control inputs: the steering angle and the longitudinal acceleration. The proposed active lane change algorithm has been successfully implemented on an autonomous vehicle and evaluated via real-world driving tests. Safe and comfortable lane changes in high-speed driving on highways have been demonstrated using our autonomous test vehicle.

scholarly journals Learning Resolution-Invariant Deep Representations for Person Re-Identification

2019 ◽  
Vol 33 ◽  
pp. 8215-8222 ◽  
Author(s):  
Yun-Chun Chen ◽  
Yu-Jhe Li ◽  
Xiaofei Du ◽  
Yu-Chiang Frank Wang
Keyword(s):  
Real World ◽  
Network Architecture ◽  
Practical Problem ◽  
Super Resolution ◽  
Low Resolution ◽  
Research Topics ◽  
Adversarial Learning ◽  
Proposed Model ◽  
Image Super Resolution ◽  
Invariant Representations

Person re-identification (re-ID) solves the task of matching images across cameras and is among the research topics in vision community. Since query images in real-world scenarios might suffer from resolution loss, how to solve the resolution mismatch problem during person re-ID becomes a practical problem. Instead of applying separate image super-resolution models, we propose a novel network architecture of Resolution Adaptation and re-Identification Network (RAIN) to solve cross-resolution person re-ID. Advancing the strategy of adversarial learning, we aim at extracting resolution-invariant representations for re-ID, while the proposed model is learned in an end-to-end training fashion. Our experiments confirm that the use of our model can recognize low-resolution query images, even if the resolution is not seen during training. Moreover, the extension of our model for semi-supervised re-ID further confirms the scalability of our proposed method for real-world scenarios and applications.

scholarly journals Using Real World Data in Virtual Development and Testing of a Path Tracking Controller for an Autonomous Vehicle

2019 ◽  
Vol 8 (12) ◽  
pp. 720-726
Keyword(s):  
Real World ◽  
Autonomous Vehicle ◽  
Field Testing ◽  
Development Project ◽  
Path Tracking ◽  
Real World Data ◽  
Human Driver ◽  
Automatic Regulator ◽  
Pros And Cons ◽  
Two Stages

The article describes an approach to development and testing of a path tracking function for an autonomous vehicle. The essence of the approach consists in combining experimental data and mathematical modeling in order to simulate operation of a path-tracking regulator in real world maneuvers. The procedure can be divided into two stages. The first one implies field-testing of the vehicle under control of a human driver with logging of the essential dynamic variables including the driving trajectory. Then the obtained data is used to validate the model of vehicle dynamics being a tool for further simulations. At the second stage, a simulation is performed with tracking of the previously logged trajectory by an automatic regulator. The results of these steps allow for comparison between the human and automatic controls with assessment of pros and cons of the latter and the ways of improving its performance. The proposed approach was implemented within a research and development project aimed at building of an experimental autonomous vehicle. The article describes the obtained results as well as the experiments and the mathematical model used for implementation of the said approach.

scholarly journals Abstractive Text Summarization by Incorporating Reader Comments

2019 ◽  
Vol 33 ◽  
pp. 6399-6406 ◽  
Author(s):  
Shen Gao ◽  
Xiuying Chen ◽  
Piji Li ◽  
Zhaochun Ren ◽  
Lidong Bing ◽  
...  
Keyword(s):  
Real World ◽  
Large Scale ◽  
Text Summarization ◽  
Experimental Results ◽  
Semantic Gap ◽  
Main Aspect ◽  
Adversarial Learning ◽  
Large Scale Dataset ◽  
Reader Comments ◽  
Abstractive Summarization

In neural abstractive summarization field, conventional sequence-to-sequence based models often suffer from summarizing the wrong aspect of the document with respect to the main aspect. To tackle this problem, we propose the task of reader-aware abstractive summary generation, which utilizes the reader comments to help the model produce better summary about the main aspect. Unlike traditional abstractive summarization task, reader-aware summarization confronts two main challenges: (1) Comments are informal and noisy; (2) jointly modeling the news document and the reader comments is challenging. To tackle the above challenges, we design an adversarial learning model named reader-aware summary generator (RASG), which consists of four components: (1) a sequence-to-sequence based summary generator; (2) a reader attention module capturing the reader focused aspects; (3) a supervisor modeling the semantic gap between the generated summary and reader focused aspects; (4) a goal tracker producing the goal for each generation step. The supervisor and the goal tacker are used to guide the training of our framework in an adversarial manner. Extensive experiments are conducted on our large-scale real-world text summarization dataset, and the results show that RASG achieves the stateof-the-art performance in terms of both automatic metrics and human evaluations. The experimental results also demonstrate the effectiveness of each module in our framework. We release our large-scale dataset for further research1.

Sign in / Sign up

Export Citation Format

Share Document