Robust UAV path planning using POMDP with limited FOV sensor

Eaton, Christopher M.; Chong, Edwin K. P.; Maciejewski, Anthony A.

doi:10.1109/ccta.2017.8062674

Cited by 21 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rock Sample also provided an independent AIG-action-simulated field-of-view limitation. [7] considered a field-of-view limitation for the tracking task of UAV. [14] proposed benchmark cases with over ten thousand states and up to a thousand observations, such as Underwater Navigation, Grasping, Homecare, and Integrated Exploration.…”

Section: Related Workmentioning

confidence: 99%

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

Shao¹,

Kong²,

Matsumura³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present Mask Atari, a new benchmark to help solve partially observable Markov decision process (POMDP) problems with Deep Reinforcement Learning (DRL)-based approaches. To achieve a simulation environment for the POMDP problems, Mask Atari is constructed based on Atari 2600 games with controllable, moveable, and learnable masks as the observation area for the target agent, especially with the active information gathering (AIG) setting in POMDPs. Given that one does not yet exist, Mask Atari provides a challenging, efficient benchmark for evaluating the methods that focus on the above problem. Moreover, the mask operation is a trial for introducing the receptive field in the human vision system into a simulation environment for an agent, which means the evaluations are not biased from the sensing ability and purely focus on the cognitive performance of the methods when compared with the human baseline. We describe the challenges and features of our benchmark and evaluate several baselines with Mask Atari.

show abstract

Section: Related Workmentioning

confidence: 99%

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

Shao¹,

Kong²,

Matsumura³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…POMDP is a mathematical model for decision analysis of the agent with partially observable and random environments. It has been successfully applied in many fields, such as path planning [21,22], system management [23 -25], and text recognition [26,27]. Here, the POMDP model is suitable to deal with the scheduling problem because of the unobservable target state.…”

Section: Problem Formulationmentioning

confidence: 99%

Sensor scheduling for ground maneuvering target tracking in presence of detection blind zone

Shan

Duan

2020

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

Continuous and stable tracking of the ground maneuvering target is a challenging problem due to the complex terrain and high clutter. A collaborative tracking method of the multisensor network is presented for the ground maneuvering target in the presence of the detection blind zone (DBZ). First, the sensor scheduling process is modeled within the partially observable Markov decision process (POMDP) framework. To evaluate the target tracking accuracy of the sensor, the Fisher information is applied to constructing the reward function. The key of the proposed scheduling method is forecasting and early decisionmaking. Thus, an approximate method based on unscented sampling is presented to estimate the target state and the multi-step scheduling reward over the prediction time horizon. Moreover, the problem is converted into a nonlinear optimization problem, and a fast search algorithm is given to solve the sensor scheduling scheme quickly. Simulation results demonstrate the proposed nonmyopic scheduling method (Non-MSM) has a better target tracking accuracy compared with traditional methods.

show abstract

“…Carlson et al ( 2013 ) proposed and compared three different strategies for estimating the change of the robot's motion, which effectively reduced the probability of collisions and avoided sources of error in industrial scenarios. Eaton et al ( 2017 ) proposed a robust Partially Observable Markov Decision Process (POMDP) formula, which provides the capability of planning and tracking with limited observations. Lv et al ( 2019 ) cited the dense connection method to improve the Q-networks structure to solve the issue of robot drift by adopting the framework of a dense network.…”

Section: Introductionmentioning

confidence: 99%

Path Planning in Localization Uncertaining Environment Based on Dijkstra Method

et al. 2022

View full text Add to dashboard Cite

Path planning obtains the trajectory from one point to another with the robot's kinematics model and environment understanding. However, as the localization uncertainty through the odometry sensors is inevitably affected, the position of the moving path will deviate further and further compared to the original path, which leads to path drift in GPS denied environments. This article proposes a novel path planning algorithm based on Dijkstra to address such issues. By combining statistical characteristics of localization error caused by dead-reckoning, the replanned path with minimum cumulative error is generated with uniforming distribution in the searching space. The simulation verifies the effectiveness of the proposed algorithm. In a real scenario with measurement noise, the results of the proposed algorithm effectively reduce cumulative error compared to the results of the conventional planning algorithm.

show abstract

Robust UAV path planning using POMDP with limited FOV sensor

Cited by 21 publications

References 11 publications

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks

Sensor scheduling for ground maneuvering target tracking in presence of detection blind zone

Path Planning in Localization Uncertaining Environment Based on Dijkstra Method

Contact Info

Product

Resources

About