More Like this

1. Tracking Multiple Ground Objects Using a Team of Unmanned Air Vehicles

   Sakamaki J.Y., Beard R.W. (January 2017, Lecture notes in control and information sciences)

   This paper proposes a system architecture for tracking multiple ground-based objects using a team of unmanned air systems (UAS). In the architecture pipeline, video data is processed by each UAS to detect motion in the image frame. The ground-based location of the detected motion is estimated using a geolocation algorithm. The subsequent data points are then process by the recently introduced Recursive RANSAC (R-RANSASC) algorithm to produce a set of tracks. These tracks are then communicated over the network and the error in the coordinate frames between vehicles must be estimated. After the tracks have been placed in the same coordinate frame, a track-to-track association algorithm is used to determine which tracks in each camera correspond to tracks in other cameras. Associated tracks are then fused using a distributed information filter. The proposed method is demonstrated on data collected from two multi-rotors tracking a person walking on the ground. 

   more » « less
2. Good Line Cutting: Towards Accurate Pose Tracking of Line-Assisted VO/VSLAM

   https://doi.org/10.1007/978-3-030-01216-8_32  

   Zhao, Y.; Vela, P.A. (October 2018, European Conference on Computer Vision)

   This paper tackles a problem in line-assisted VO/VSLAM: accurately solving the least squares pose optimization with unreliable 3D line input. The solution we present is good line cutting, which extracts the most-informative sub-segment from each 3D line for use within the pose optimization formulation. By studying the impact of line cutting towards the information gain of pose estimation in line-based least squares problem, we demonstrate the applicability of improving pose estimation accuracy with good line cutting. To that end, we describe an efficient algorithm that approximately approaches the joint optimization problem of good line cutting. The proposed algorithm is integrated into a state-of-the-art line-assisted VSLAM system. When evaluated in two target scenarios of line-assisted VO/VSLAM, low-texture and motion blur, the accuracy of pose tracking is improved, while the robustness is preserved. 

   more » « less
3. A Finite-Time Stable Observer for Relative Attitude Estimation

   https://doi.org/10.1109/CDC40024.2019.9029806  

   Wang, Ningshan; Hamrah, Reza; Sanyal, Amit K. (December 2019, 2019 IEEE 58th Conference on Decision and Control (CDC))

   Relative motion estimation of one rigid body with respect to another is a problem that has immediate applications to formations and maneuvers involving multiple unmanned vehicles or collision avoidance between vehicles. A finite-time stable observer for relative attitude estimation of a rigid object using onboard sensors on an unmanned vehicle, is developed and presented here. This observer assumes sensor inputs from onboard vision and inertial sensors, with the vision sensors measuring at least three points on the object whose relative locations with respect to a body-fixed frame on the object are also assumed to be known. In the absence of any measurement noise, the estimated relative attitude is shown to converge to the actual relative pose in a finite-time stable manner. Numerical simulations indicate that this relative attitude observer is robust to persistent measurement errors and converges to a bounded neighborhood of the true attitude. 

   more » « less
4. Optimal Measurement Policy for Linear Measurement Systems with Applications to UAV Network Topology Prediction

   https://doi.org/10.1109/TVT.2019.2956132  

   Razi, Abolfazl (November 2019, IEEE Transactions on Vehicular Technology)

   Dynamic network topology can pose important challenges to communication and control protocols in networks of autonomous vehicles. For instance, maintaining connectivity is a key challenge in unmanned aerial vehicle (UAV) networks. However, tracking and computational resources of the observer module might not be sufficient for constant monitoring of all surrounding nodes in large-scale networks. In this paper, we propose an optimal measurement policy for network topology monitoring under constrained resources. To this end, We formulate the localization of multiple objects in terms of linear networked systems and solve it using Kalman filtering with intermittent observation. The proposed policy includes two sequential steps. We first find optimal measurement attempt probabilities for each target using numerical optimization methods to assign the limited number of resources among targets. The optimal resource allocation follows a waterfall-like solution to assign more resources to targets with lower measurement success probability. This provides a 10% to 60% gain in prediction accuracy. The second step is finding optimal on-off patterns for measurement attempts for each target over time. We show that a regular measurement pattern that evenly distributed resources over time outperforms the two extreme cases of using all measurement resources either in the beginning or at the end of the measurement cycle. Our proof is based on characterizing the fixed-point solution of the error covariance matrix for regular patterns. Extensive simulation results confirm the optimality of the most alternating pattern with up to 10-fold prediction improvement for different scenarios. These two guidelines define a general policy for target tracking under constrained resources with applications to network topology prediction of autonomous systems 

   more » « less
5. Monocular Vision-Based Localization and Pose Estimation with a Nudged Particle Filter and Ellipsoidal Confidence Tubes

   https://doi.org/10.1142/S2301385023500061  

   Lin, Tony X.; Coogan, Samuel; Lofaro, Daniel M.; Sofge, Donald A.; Zhang, Fumin (January 2023, Unmanned Systems)

   This paper proposes a nudged particle filter for estimating the pose of a camera mounted on flying robots collecting a video sequence. The nudged particle filter leverages two image-to-pose and pose-to-image neural networks trained in an auto-encoder fashion with a dataset of pose-labeled images. Given an image, the retrieved camera pose using the image-to-pose network serves as a special particle to nudge the set of particles generated from the particle filter while the pose-to-image network serves to compute the likelihoods of each particle. We demonstrate that such a nudging scheme effectively mitigates low likelihood samplings during the particle propagation step. Ellipsoidal confidence tubes are constructed from the set of particles to provide a computationally efficient bound on localization error. When an ellipsoidal tube self-intersects, the probability volume of the intersection can be significantly shrunken using a novel Dempster–Shafer probability mass assignment algorithm. Starting from the intersection, a loop closure procedure is developed to move backward in time to shrink the volumes of the entire ellipsoidal tube. Experimental results using the Georgia Tech Miniature Autonomous Blimp platform are provided to demonstrate the feasibility and effectiveness of the proposed algorithms in providing localization and pose estimation based on monocular vision. 

   more » « less