Abstract
Correct ego-lane index estimation is essential for lane change and decision making for intelligent vehicles, especially in global navigation satellite system (GNSS)-challenged environments. To achieve this, we propose an ego-lane index estimation approach in an urban scenario based on particle filter (PF). The particles are initialized and propagated by dead reckoning with inertial measurement unit (IMU) and odometry. A lane-level map is used to navigate the particles taking advantage of topologic and geometric information of lanes. GNSS single-point positioning (SPP) can provide position estimation with meter-level accuracy in urban environments, which can limit drift introduced by dead reckoning for updating the weight of each particle. Light detection and ranging (LiDAR) is a common sensor in an intelligent vehicle. A LiDAR-based road boundary detection method provides distance measurements from the vehicle to the left/right road boundaries, which provides a measurement for importance weighting. However, the high precision of the LiDAR measurements may put a tight constraint on the distribution of particles, which can lead to particle degeneration with sparse particle sets. To deal with this problem, we propose a novel step that shifts particles laterally based on LiDAR measurements instead of importance weighting in the traditional PF scheme. We tested our methods on an urban expressway at a low traffic volume period to ensure road boundaries can be detected by LiDAR measurements at most time steps. Experimental results prove that our improved PF scheme can correctly estimate ego-lane index at all time steps, while the traditional PF scheme produces wrong estimations at some time steps.
Highlights
Ego-lane index estimation refers to the determination of the lane index currently occupied by the vehicle, which is essential for intelligent vehicles, as it can recommend lane changes if needed
Rabe et al [20] generated hypotheses of trajectory with map data and lane changes to describe several driving possibilities, aligned the hypotheses to the trajectory generated from vehicle odometry and yaw rate in a weighted least-squares sense, and determined the likelihood of the ego-vehicle being on a certain lane
To take advantage of this information, in this paper, we proposed a particle filter (PF) framework using a Light detection and ranging (LiDAR)-based road boundary detection, a lane-level map, and global navigation satellite system (GNSS)/inertial measurement unit (IMU)/odometry navigation data
Summary
Ego-lane index estimation refers to the determination of the lane index currently occupied by the vehicle, which is essential for intelligent vehicles, as it can recommend lane changes if needed. Rabe et al [20] generated hypotheses of trajectory with map data and lane changes to describe several driving possibilities, aligned the hypotheses to the trajectory generated from vehicle odometry and yaw rate in a weighted least-squares sense, and determined the likelihood of the ego-vehicle being on a certain lane They proposed a PF framework to this ego-lane index estimation problem [21]. Ballardini et al [23] proposed a probabilistic framework for highway-like scenarios using a hidden Markov model (HMM) with a transient failure model, which considered inaccurate or missing road marking detections They used GNSS measure and the number of lanes of the road, retrieved from a map service OpenStreetMap prior to enhancement of the visual ego-lane index estimation [24]. An important contribution of this paper is that we used the LiDAR measurement to shift particles laterally instead of updating the particle weight for each particle, which successfully avoids particle degradation
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
