Abstract--In this paper, we propose a non-myopic sensor management algorithm for multi-target tracking, with multiple sensors operating in the same surveillance area. The algorithm is based on multi-Bernoulli filtering and selects the actions that solve a non-myopic minimisation problem, where the cost function is the mean square generalised optimal sub-pattern assignment (GOSPA) error, over a future time window. For tractability, the sensor management algorithm actually uses an upper bound of the GOSPA error and is implemented via Monte Carlo Tree Search (MCTS). The sensors have the ability to jointly optimise and select their actions with the considerations of all other sensors in the surveillance area. The benefits of the proposed algorithm are analysed via simulations. ENSOR management can be defined as the dynamic re-tasking of agile sensors to achieve an operational objective [1]. Sensors can be agile in a multitude of ways, from physically repositioning, changing direction or selecting a sensing mode. Myopic sensor management, sometimes called greedy sensor management, optimises the sensor resources for the immediate benefit of the system, not considering the long term effects of the actions being selected now. Non-myopic sensor management operates on the policy of considering these long-term effects of the actions selected now. Whilst it has an increased computational demand, non-myopic planning often produces more desirable results [2], [3].

High-definition map with accurate lane-level information is crucial for autonomous driving, but the creation of these maps is a resource-intensive process. To this end, we present a cost-effective solution to create lane-level roadmaps using only the global navigation satellite system (GNSS) and a camera on customer vehicles. Our proposed solution utilizes a prior standard-definition (SD) map, GNSS measurements, visual odometry, and lane marking edge detection points, to simultaneously estimate the vehicle's 6D pose, its position within a SD map, and also the 3D geometry of traffic lines. This is achieved using a Bayesian simultaneous localization and multi-object tracking filter, where the estimation of traffic lines is formulated as a multiple extended object tracking problem, solved using a trajectory Poisson multi-Bernoulli mixture (TPMBM) filter. In TPMBM filtering, traffic lines are modeled using B-spline trajectories, and each trajectory is parameterized by a sequence of control points. The proposed solution has been evaluated using experimental data collected by a test vehicle driving on highway. Preliminary results show that the traffic line estimates, overlaid on the satellite image, generally align with the lane markings up to some lateral offsets.

In this paper, we demonstrate that deep learning based method can be used to fuse multi-object densities. Given a scenario with several sensors with possibly different field-of-views, tracking is performed locally in each sensor by a tracker, which produces random finite set multi-object densities. To fuse outputs from different trackers, we adapt a recently proposed transformer-based multi-object tracker, where the fusion result is a global multi-object density, describing the set of all alive objects at the current time. We compare the performance of the transformer-based fusion method with a well-performing model-based Bayesian fusion method in several simulated scenarios with different parameter settings using synthetic data. The simulation results show that the transformer-based fusion method outperforms the model-based Bayesian method in our experimental scenarios.

--In this paper, we show the spooky effect at a distance that arises in optimal estimation of multiple targets with the optimal sub-pattern assignment (OSPA) metric. This effect refers to the fact that if we have several independent potential targets at distant locations, a change in the probability of existence of one of them can completely change the optimal estimation of the rest of the potential targets. As opposed to OSPA, the generalised OSPA (GOSPA) metric ( α 2) penalises localisation errors for properly detected targets, false targets and missed targets. As a consequence, optimal GOSPA estimation aims to lower the number of false and missed targets, as well as the localisation error for properly detected targets, and avoids the spooky effect. Multiple target estimation is an inherent part of many applications such as surveillance, self-driving vehicles, and air-traffic control [1]-[3]. The special characteristic of multiple target estimation is that it requires the estimation of the number of targets, which is unknown, as well as their states. In a Bayesian paradigm, given some noisy observations of a random variable of interest, all information about this variable is contained in its posterior probability density function [4]. Given the posterior and a cost function, optimal estimation is performed by minimising the expected value of this cost function with respect to the posterior [5], [6]. For example, for random vectors of fixed dimensionality, if the cost function is the square error, the optimal estimator, which is referred to as the minimum mean square error estimator, is the posterior mean.

This paper addresses the mapping problem. Using a conjugate prior form, we derive the exact theoretical batch multi-object posterior density of the map given a set of measurements. The landmarks in the map are modeled as extended objects, and the measurements are described as a Poisson process, conditioned on the map. We use a Poisson process prior on the map and prove that the posterior distribution is a hybrid Poisson, multi-Bernoulli mixture distribution. We devise a Gibbs sampling algorithm to sample from the batch multi-object posterior. The proposed method can handle uncertainties in the data associations and the cardinality of the set of landmarks, and is parallelizable, making it suitable for large-scale problems. The performance of the proposed method is evaluated on synthetic data and is shown to outperform a state-of-the-art method.