arXiv subjects

Jiajie Yu

Publications and source records attributed to Jiajie Yu.

5 recordsLinked to original sources

arXiv2025

DOA: A Degeneracy Optimization Agent with Adaptive Pose Compensation Capability based on Deep Reinforcement Learning

Particle filter-based 2D-SLAM is widely used in indoor localization tasks due to its efficiency. However, indoor environments such as long straight corridors can cause severe degeneracy problems in SLAM. In this paper, we use Proximal Policy Optimization (PPO) to train an adaptive degeneracy optimization agent (DOA) to address degeneracy problem. We propose a systematic methodology to address three critical challenges in traditional supervised learning frameworks: (1) data acquisition bottlenecks in degenerate dataset, (2) inherent quality deterioration of training samples, and (3) ambiguity in annotation protocol design. We design a specialized reward function to guide the agent in developing perception capabilities for degenerate environments. Using the output degeneracy factor as a reference weight, the agent can dynamically adjust the contribution of different sensors to pose optimization. Specifically, the observation distribution is shifted towards the motion model distribution, with the step size determined by a linear interpolation formula related to the degeneracy factor. In addition, we employ a transfer learning module to endow the agent with generalization capabilities across different environments and address the inefficiency of training in degenerate environments. Finally, we conduct ablation studies to demonstrate the rationality of our model design and the role of transfer learning. We also compare the proposed DOA with SOTA methods to prove its superior degeneracy detection and optimization capabilities across various environments.

cs.RO↗

arXiv2024

Large Language Model-Enhanced Reinforcement Learning for Generic Bus Holding Control Strategies

Bus holding control is a widely-adopted strategy for maintaining stability and improving the operational efficiency of bus systems. Traditional model-based methods often face challenges with the low accuracy of bus state prediction and passenger demand estimation. In contrast, Reinforcement Learning (RL), as a data-driven approach, has demonstrated great potential in formulating bus holding strategies. RL determines the optimal control strategies in order to maximize the cumulative reward, which reflects the overall control goals. However, translating sparse and delayed control goals in real-world tasks into dense and real-time rewards for RL is challenging, normally requiring extensive manual trial-and-error. In view of this, this study introduces an automatic reward generation paradigm by leveraging the in-context learning and reasoning capabilities of Large Language Models (LLMs). This new paradigm, termed the LLM-enhanced RL, comprises several LLM-based modules: reward initializer, reward modifier, performance analyzer, and reward refiner. These modules cooperate to initialize and iteratively improve the reward function according to the feedback from training and test results for the specified RL-based task. Ineffective reward functions generated by the LLM are filtered out to ensure the stable evolution of the RL agents' performance over iterations. To evaluate the feasibility of the proposed LLM-enhanced RL paradigm, it is applied to extensive bus holding control scenarios that vary in the number of bus lines, stops, and passenger demand. The results demonstrate the superiority, generalization capability, and robustness of the proposed paradigm compared to vanilla RL strategies, the LLM-based controller, physics-based feedback controllers, and optimization-based controllers. This study sheds light on the great potential of utilizing LLMs in various smart mobility applications.

cs.AI↗

arXiv2024

Online Prediction-Assisted Safe Reinforcement Learning for Electric Vehicle Charging Station Recommendation in Dynamically Coupled Transportation-Power Systems

With the proliferation of electric vehicles (EVs), the transportation network and power grid become increasingly interdependent and coupled via charging stations. The concomitant growth in charging demand has posed challenges for both networks, highlighting the importance of charging coordination. Existing literature largely overlooks the interactions between power grid security and traffic efficiency. In view of this, we study the en-route charging station (CS) recommendation problem for EVs in dynamically coupled transportation-power systems. The system-level objective is to maximize the overall traffic efficiency while ensuring the safety of the power grid. This problem is for the first time formulated as a constrained Markov decision process (CMDP), and an online prediction-assisted safe reinforcement learning (OP-SRL) method is proposed to learn the optimal and secure policy by extending the PPO method. To be specific, we mainly address two challenges. First, the constrained optimization problem is converted into an equivalent unconstrained optimization problem by applying the Lagrangian method. Second, to account for the uncertain long-time delay between performing CS recommendation and commencing charging, we put forward an online sequence-to-sequence (Seq2Seq) predictor for state augmentation to guide the agent in making forward-thinking decisions. Finally, we conduct comprehensive experimental studies based on the Nguyen-Dupuis network and a large-scale real-world road network, coupled with IEEE 33-bus and IEEE 69-bus distribution systems, respectively. Results demonstrate that the proposed method outperforms baselines in terms of road network efficiency, power grid safety, and EV user satisfaction. The case study on the real-world network also illustrates the applicability in the practical context.

cs.CE↗

arXiv2023

Perimeter Control with Heterogeneous Metering Rates for Cordon Signals: A Physics-Regularized Multi-Agent Reinforcement Learning Approach

Perimeter Control (PC) strategies have been proposed to address urban road network control in oversaturated situations by regulating the transfer flow of the Protected Network (PN) based on the Macroscopic Fundamental Diagram (MFD). The uniform metering rate for cordon signals in most existing studies overlooks the variance of local traffic states at the intersection level, which may cause severe local traffic congestion and degradation of the network stability. PC strategies with heterogeneous metering rates for cordon signals allow precise control for the perimeter but the complexity of the problem increases exponentially with the scale of the PN. This paper leverages a Multi-Agent Reinforcement Learning (MARL)-based traffic signal control framework to decompose this PC problem, which considers heterogeneous metering rates for cordon signals, into multi-agent cooperation tasks. Each agent controls an individual signal located in the cordon, decreasing the dimension of action space for the controller compared to centralized methods. A physics regularization approach for the MARL framework is proposed to ensure the distributed cordon signal controllers are aware of the global network state by encoding MFD-based knowledge into the action-value functions of the local agents. The proposed PC strategy is operated as a two-stage system, with a feedback PC strategy detecting the overall traffic state within the PN and then distributing local instructions to cordon signals controllers in the MARL framework via the physics regularization. Through numerical tests with different demand patterns in a microscopic traffic environment, the proposed PC strategy shows promising robustness and transferability. It outperforms state-of-the-art feedback PC strategies in increasing network throughput, decreasing distributed delay for gate links, and reducing carbon emissions.

cs.AI↗

arXiv2023

A Heuristic Autonomous Exploration Method Based on Environmental Information Gain During Quadrotor Flight

Autonomous exploration is a widely studied fundamental application in the field of quadrotors, which requires them to automatically explore unknown space to obtain complete information about the environment. The frontier-based method, which is one of the representative works on autonomous exploration, drives autonomous determination by the definition of frontier information, so that complete information about the environment is available to the quadrotor. However, existing frontier-based methods are able to accomplish the task but still suffer from inefficient exploration. How to improve the efficiency of autonomous exploration is the focus of current research. Typical problems include slow frontier generation, which affects real-time viewpoint determination, and insufficient determination methods that affect the quality of viewpoints. Therefore, to overcome these problems, this paper proposes a two-level viewpoint determination method for frontier-based autonomous exploration. Firstly, a sampling-based frontier detection method is presented for faster frontier generation, which improves the immediacy of environmental representation compared to traditional traversal-based methods. Secondly, we consider the access to environmental information during flight for the first time and design an innovative heuristic evaluation function to decide on a high-quality viewpoint as the next local navigation target in each exploration iteration. We conducted extensive benchmark and real-world tests to validate our method. The results confirm that our method optimizes the frontier search time by 85%, the exploration time by around 20-30%, and the exploration path by 25-35%.

cs.RO↗