Abstract
RTOB-SLAM is a new low-computation framework for real-time onboard simultaneous localization and mapping (SLAM) and obstacle avoidance for autonomous vehicles. A low-resolution 2D laser scanner is used and a small form-factor computer perform all computations onboard. The SLAM process is based on laser scan matching with the iterative closest point technique to estimate the vehicle’s current position by aligning the new scan with the map. This paper describes a new method which uses only a small subsample of the global map for scan matching, which improves the performance and allows for a map to adapt to a dynamic environment by partly forgetting the past. A detailed comparison between this method and current state-of-the-art SLAM frameworks is given, together with a methodology to choose the parameters of the RTOB-SLAM. The RTOB-SLAM has been implemented in ROS and perform well in various simulations and real experiments.
Highlights
The iterative closest point (ICP) scan matching is done with the Point Cloud Library (PCL)
A real-time onboard SLAM algorithm named RTOB-SLAM has been developed to enable simultaneous localization and mapping with a low-resolution 2D laser scanner running on a small form-factor computer
This approach is suitable for (a) light-weight vehicle which possess limited computing power such as autonomous aerial vehicles, and for (b) ground vehicles for which power consumption is a concern. This new method is based on ICP scan matching and introduced the use of probabilitydensity function in order to obtain a subsample of the global two-dimensional map, which is used for scan-matching
Summary
Over the last couple of years, ground and air autonomous vehicles have become incredibly popular in academia and industry. These sensors give an estimate of the position but do not provide any information on the environment, and have limited accuracy -in particular for GPS To overcome both limitations, cameras [2,3] and laser scanners are commonly used to sense the surroundings. While fast and high-resolution cameras are relatively small and light-weight, the post-processing of the data requires powerful computers which are usually unsuited aboard a lightweight autonomous vehicle. This makes such vehicles dependent on a powerful ground-station computer. The paragraph reviews commonly-used methods for SLAM and obstacle avoidance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
