Developing logic-based specification for real-time autonomous systems

Autonomous driving is a safety-critical application that requires a high-level understanding of computer vision with real-time inference. In this study, we focus on the computational efficiency of an important factor by improving the running time and performing multiple tasks simultaneously for practical applications. We propose a fast and accurate multi-task learning-based architecture for joint segmentation of drivable area, lane line, and classification of the scene. An encoder-decoder architecture efficiently handles input frames through shared representation. A comprehensive understanding of the driving environment is improved by generalization and regularization from different tasks. The proposed method learns end-to-end through multi-task learning on a very challenging Berkeley Deep Drive dataset and shows its robustness for three tasks in autonomous driving. Experimental results show that the proposed method outperforms other multi-task learning approaches in both speed and accuracy. The computational efficiency of the method was over 93.81 fps at inference, enabling execution in real-time.

Download Full-text

Hardware-in-the-loop simulation for real-time software verification of an autonomous underwater robot

International Journal of Intelligent Unmanned Systems ◽

10.1108/ijius-12-2015-0016 ◽

2016 ◽

Vol 4 (3) ◽

pp. 163-181

Author(s):

Pouria Sarhadi ◽

Reza Nad Ali Niachari ◽

Morteza Pouyan Rad ◽

Javad Enayati

Keyword(s):

Software Engineering ◽

Real Time ◽

Autonomous Systems ◽

Systems Design ◽

Development Stage ◽

Underwater Robot ◽

Real Time System ◽

Content Type ◽

The Real ◽

Time Performance

Purpose The purpose of this paper is to propose a software engineering procedure for real-time software development and verification of an autonomous underwater robotic system. High performance and robust software are one of the requirements of autonomous systems design. A simple error in the software can easily lead to a catastrophic failure in a complex system. Then, a systematic procedure is presented for this purpose. Design/methodology/approach This paper utilizes software engineering tools and hardware-inthe-loop (HIL) simulations for real-time system design of an autonomous underwater robot. Findings In this paper, the architecture of the system is extracted. Then, using software engineering techniques a suitable structure for control software is presented. Considering the desirable targets of the robot, suitable algorithms and functions are developed. After the development stage, proving the real-time performance of the software is disclosed. Originality/value A suitable approach for analyzing the real-time performance is presented. This approach is implemented using HIL simulations. The developed structure is applicable to other autonomous systems.

Download Full-text