arXiv subjects

Shaoming He

Publications and source records attributed to Shaoming He.

22 records · Page 2Linked to original sources

arXiv2021

Information-Weighted Consensus Filter with Partial Information Exchange

In this paper, the information-weighted consensus filter (ICF) with partial information exchange is proposed to reduce the bandwidth of the signals transmitted between the sensor nodes and guarantee its convergence to the centralized Kalman filter (CKF). In the proposed algorithm, a part of information chosen with the entry selection matrix is transmitted to the sensor nodes in the neighborhood at each consensus step, and consensus averaging is conducted at each sensor node with the partial and the local information. This ensures that the proposed distributed estimation algorithm converges to the centralized algorithm, while allowing the proposed algorithm to achieve bandwidth reduction of the signals transmitted between the sensors. With the proposed algorithm, the stability of the estimation error dynamics is proven and the convergence to the centralized algorithm is mathematically shown using the property of the average consensus. Simulations are conducted to validate the proposed ICF with partial information exchange and the related theoretical findings.

cs.IT↗

arXiv2021

A Learning-Based Computational Impact Time Guidance

This paper investigates the problem of impact-time-control and proposes a learning-based computational guidance algorithm to solve this problem. The proposed guidance algorithm is developed based on a general prediction-correction concept: the exact time-to-go under proportional navigation guidance with realistic aerodynamic characteristics is estimated by a deep neural network and a biased command to nullify the impact time error is developed by utilizing the emerging reinforcement learning techniques. The deep neural network is augmented into the reinforcement learning block to resolve the issue of sparse reward that has been observed in typical reinforcement learning formulation. Extensive numerical simulations are conducted to support the proposed algorithm.

cs.LG↗

arXiv2020

A Domain-Knowledge-Aided Deep Reinforcement Learning Approach for Flight Control Design

This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, we suggest to leverage domain knowledge available in learning to improve learning efficiency and generalisability. More specifically, the proposed approach fixes the autopilot structure as typical three-loop autopilot and deep reinforcement learning is utilised to learn the autopilot gains. To solve the flight control problem, we then formulate a Markovian decision process with a proper reward function that enable the application of reinforcement learning theory. Another type of domain knowledge is exploited for defining the reward function, by shaping reference inputs in consideration of important control objectives and using the shaped reference inputs in the reward function. The state-of-the-art deep deterministic policy gradient algorithm is utilised to learn an action policy that maps the observed states to the autopilot gains. Extensive empirical numerical simulations are performed to validate the proposed computational control algorithm.

cs.AI↗

arXiv2019

Sample Greedy Gossip for Distributed Network-Wide Average Computation

This paper investigates the problem of distributed network-wide averaging and proposes a new greedy gossip algorithm. Instead of finding the optimal path of each node in a greedy manner, the proposed approach utilises a suboptimal communication path by performing greedy selection among randomly selected active local nodes. Theoretical analysis on convergence speed is also performed to investigate the characteristics of the proposed algorithm. The main feature of the new algorithm is that it provides great flexibility and well balance between communication cost and convergence performance introduced by the stochastic sampling strategy. Extensive numerical simulations are performed to validate the analytic findings.

eess.SY↗