Fast-Tracker: A Robust Aerial System for Tracking Agile Target in Cluttered Environments

Han, Zhi-Chao; Zhang, Ruibin; Pan, Neng; Xu, Chao; Gao, Fei

doi:10.48550/arxiv.2011.03968

Cited by 10 publications

(41 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We specifically aim to cover two aspects: (i) the occlusion/collision model or in other words the algebraic form of C f ree and (ii) the algorithms employed to solve the target-tracking trajectory optimization problem. Note that some existing approaches like [13] simplify the problem by ignoring the effect of occlusion and focus only on collision avoidance while tracking. In our experimentation, we found that such an approach can work if the quadrotor equipped with a downward-looking camera is always allowed to hover over the target.…”

Section: B Trajectory Optimization For Target Trackingmentioning

confidence: 99%

“…Due to the differential flatness property, the motion along x, y, z axes, and the yaw motion are all decoupled. These assumptions are standard in the existing literature on quadrotor motion planning, including those dealing specifically with target tracking [13] and dronecinematography [25]. Finally, like [25], [12], we assume that the variation of pitch and roll angles have minimal effect on the visibility of the target.…”

Section: A Assumptionsmentioning

confidence: 99%

“…• Independent Camera Control: Similar to works like [13], [25], we assume that the camera motion is decoupled from the quadrotors body motion. Thus, we can always align the camera of the quadrotor to the LOS vector.…”

Section: A Assumptionsmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Multi-Convex Model Predictive Control for Occlusion Free Target Tracking

Masnavi¹,

Adajania²,

Kruusamäe³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper proposes a Model Predictive Control (MPC) algorithm for target tracking amongst static and dynamic obstacles. Our main contribution lies in improving the computational tractability and reliability of the underlying nonconvex trajectory optimization. The result is an MPC algorithm that runs real-time on laptops and embedded hardware devices such as Jetson TX2. Our approach relies on novel reformulations for the tracking, collision, and occlusion constraints that induce a multi-convex structure in the resulting trajectory optimization. We exploit these mathematical structures using the split Bregman Iteration technique, eventually reducing our MPC to a series of convex Quadratic Programs solvable in a few milliseconds. The fast re-planning of our MPC allows for occlusion and collision-free tracking in complex environments even while considering a simple constant-velocity prediction for the target trajectory and dynamic obstacles. We perform extensive bench-marking in a realistic physics engine and show that our MPC outperforms the state-of-the-art algorithms in visibility, smoothness, and computation-time metrics.1 Non-convex optimizations have the so-called trust-region (or line-search) constraints that limit the progress that the optimizer can make towards the individual solutions between subsequent iterations

show abstract

Section: B Trajectory Optimization For Target Trackingmentioning

confidence: 99%

Section: A Assumptionsmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Multi-Convex Model Predictive Control for Occlusion Free Target Tracking

Masnavi¹,

Adajania²,

Kruusamäe³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Therefore, it cannot be used with general unknown environments and targets. Han et al [2] propose a safe tracking trajectory planner consisting of a target informed kinodynamic searching front-end and a spatialtemporal optimal trajectory planning back-end. However, the optimization formulation of the latter trades off minimizing energy and time, which is entirely inconsistent with the original tracking problem.…”

Section: Related Workmentioning

confidence: 99%

“…We benchmark our method with Han's [2] and Wang's [3] work in simulation. All the simulation experiments are run on a desktop equipped with an Intel Core i7-6700 CPU.…”

Section: Simulation and Benchmark Comparisonsmentioning

confidence: 99%

Elastic Tracker: A Spatio-temporal Trajectory Planner Flexible Aerial Tracking

Ji¹,

Pan²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This paper proposes Elastic Tracker, a flexible trajectory planning framework that can deal with challenging tracking tasks with guaranteed safety and visibility. Firstly, an object detection and intension-free motion prediction method is designed. Then an occlusion-aware path finding method is proposed to provide a proper topology. A smart safe flight corridor generation strategy is designed with the guiding path. An analytical occlusion cost is evaluated. Finally, an effective trajectory optimization approach enables to generate a spatiotemporal optimal trajectory within the resultant flight corridor. Particular formulations are designed to guarantee both safety and visibility, with all the above requirements optimized jointly. The experimental results show that our method works more robustly but with less computation than the existing methods, even in some challenging tracking tasks.

show abstract

Fast‐Tracker 2.0: Improving autonomy of aerial tracking with active vision and human location regression

Pan

Zhang

Yang

et al. 2021

IET Cyber-Syst and Robotics

Self Cite

View full text Add to dashboard Cite

In recent years, several progressive studies promote the development of aerial tracking. One of the representative studies is our previous work Fast‐Tracker which is applicable to various challenging tracking scenarios. However, it suffers from two main drawbacks: (1) the oversimplification in target detection by using artificial markers and (2) the contradiction between simultaneous target and environment perception with limited onboard vision. In this study, we upgrade the target detection in Fast‐Tracker to detect and localise a human target based on deep learning and non‐linear regression to solve the former problem. For the latter one, we equip the quadrotor system with 360° active vision on a customised gimbal camera. Furthermore, we improve the tracking trajectory planning in Fast‐Tracker by incorporating an occlusion‐aware mechanism that generates observable tracking trajectories. Comprehensive real‐world tests confirm the proposed system's robustness and real‐time capability. Benchmark comparisons with Fast‐Tracker validate that the proposed system presents better tracking performance even when performing more difficult tracking tasks. The cover image is based on the Original Article Fast‐Tracker 2.0: Improving autonomy of aerial tracking with active vision and human location regression by Can Cui et al., https://doi.org/10.1049/csy2.12033.

show abstract

Fast-Tracker: A Robust Aerial System for Tracking Agile Target in Cluttered Environments

Cited by 10 publications

References 14 publications

Real-Time Multi-Convex Model Predictive Control for Occlusion Free Target Tracking

Real-Time Multi-Convex Model Predictive Control for Occlusion Free Target Tracking

Elastic Tracker: A Spatio-temporal Trajectory Planner Flexible Aerial Tracking

Fast‐Tracker 2.0: Improving autonomy of aerial tracking with active vision and human location regression

Contact Info

Product

Resources

About