Search Results

With improvements in electronics and integrated safety systems, modern day cars are much safer than their predecessors. Unfortunately, cost is a very strong driving factor, when it comes to installation of a multitude of these safety systems on mid and low-segment cars. In this paper, we propose a novel integrated system of sensors that are strategically arranged around a car in order to provide safety at a reasonable cost. This generic framework of sensors would assist the driver under various driving scenarios like collision warning (forward and rear), overtake assist, parallel parking assist and adaptive cruise control. An invention disclosure has been filed with the Patent Cooperation Treaty for this work [8].

Traffic information is very useful in planning and designing of road transport, ensuring efficient administration of road traffic, transportation agencies as well as for the convenience of road users. Traffic can be measured in terms of speed, density and flow. In this paper, we propose two different methods to measure traffic in terms of density and flow. The set up for the proposed traffic monitoring system includes a camera placed at a height from ground looking downward on the road, such that its field of view is perpendicular to the direction of motion of the traffic. The images of the road are continuously captured by the camera and processed to determine the traffic. The first method uses Gaussian Mixture Modeling (GMM) to detect vehicles. Density is calculated in terms of area occupied by the vehicles on the road. Another method of measuring the traffic flow is proposed that is based on calculation of edge points on a horizontal line drawn in the image.

A two-stage spool valve system is common in the hydraulic system of an off-road vehicle and used as hydraulics control element for controlling the hydraulic cylinder. Off-road vehicle industries mostly use a fixed-gain PID based controller for the flow control of the two-stage spool valve system. A hydraulic spool valve system exhibits highly nonlinear behavior, which makes it challenging to design a PID based controller to control its dynamics. This paper presents a method for the dynamic system model development of the two-stage spool valve system. This model will be useful to study the impact on the valve dynamics due to lubricating oil properties variation to avoid the potential system hazards and machine failure scenarios. An alternative control system design approach is also proposed based on the gain-scheduled control technique, wherein the non-linear dynamics of the valve system is linearized at different equilibrium points and PID gains are scheduled at these points.

The potential to reduce the cost of embedded software by standardizing the application behavior for Automotive Body and Comfort domain functions is explored in this paper. AUTOSAR, with its layered architecture and a standard definition of the interfaces for Body and Comfort application functions, has simplified the exchangeability of software components. A further step is to standardize the application behavior, by developing standard specifications for common Body and Comfort functions. The corresponding software components can be freely exchanged between different OEM/Tier-1 users, even if developed independently by multiple suppliers. In practice, individual OEM users may need to maintain some distinction in the functionality. A method of categorizing the specifications as ‘common’ and ‘unique’, and to configure them for individual applications is proposed. This allows feature variability by means of relatively simple adapter functions.

Dense depth estimation is a critical application in the field of robotics and machine vision where the depth perception is essential. Unlike traditional approaches which use expensive sensors such as LiDAR (Light Detection and Ranging) devices or stereo camera setup, the proposed approach for depth estimation uses a single camera mounted on a rotating platform. This proposed setup is an effective replacement to usage of multiple cameras, which provide around view information required for some operations in the domain of autonomous vehicles and robots. Dense depth estimation of local scene is performed using the proposed setup. This is a novel, however challenging task because baseline distance between camera positions inversely affect common regions between images. The proposed work involves dense two view reconstruction and depth map merging to obtain a reliable large dense depth map.