Wenxuan Wang

Wenxuan Wang, Lexing Zhang, Jiale Lei et al.

Accurate vehicle acceleration prediction is critical for intelligent driving control and energy efficiency management, particularly in environments with complex driving behavior dynamics. This paper proposes a general short-term vehicle acceleration prediction framework that jointly models environmental influence and individual driving behavior. The framework adopts a dual input design by incorporating environmental sequences, constructed from historical traffic variables such as percentile-based speed and acceleration statistics of multiple vehicles at specific spatial locations, capture group-level driving behavior influenced by the traffic environment. In parallel, individual driving behavior sequences represent motion characteristics of the target vehicle prior to the prediction point, reflecting personalized driving styles. These two inputs are processed using an LSTM Seq2Seq model enhanced with an attention mechanism, enabling accurate multi-step acceleration prediction. To demonstrate the effectiveness of the proposed method, an empirical study was conducted using high resolution radar video fused trajectory data collected from the exit section of the Guangzhou Baishi Tunnel. Drivers were clustered into three categories conservative, moderate, and aggressive based on key behavioral indicators, and a dedicated prediction model was trained for each group to account for driver heterogeneity.Experimental results show that the proposed method consistently outperforms four baseline models, yielding a 10.9% improvement in accuracy with the inclusion of historical traffic variables and a 33% improvement with driver classification. Although prediction errors increase with forecast distance, incorporating environment- and behavior-aware features significantly enhances model robustness.

Jingliang Duan, Dongjie Yu, Shengbo Eben Li et al.

In this paper, we propose a new state representation method, called encoding sum and concatenation (ESC), for the state representation of decision-making in autonomous driving. Unlike existing state representation methods, ESC is applicable to a variable number of surrounding vehicles and eliminates the need for manually pre-designed sorting rules, leading to higher representation ability and generality. The proposed ESC method introduces a representation neural network (NN) to encode each surrounding vehicle into an encoding vector, and then adds these vectors to obtain the representation vector of the set of surrounding vehicles. By concatenating the set representation with other variables, such as indicators of the ego vehicle and road, we realize the fixed-dimensional and permutation invariant state representation. This paper has further proved that the proposed ESC method can realize the injective representation if the output dimension of the representation NN is greater than the number of variables of all surrounding vehicles. This means that by taking the ESC representation as policy inputs, we can find the nearly optimal representation NN and policy NN by simultaneously optimizing them using gradient-based updating. Experiments demonstrate that compared with the fixed-permutation representation method, the proposed method improves the representation ability of the surrounding vehicles, and the corresponding approximation error is reduced by 62.2%.

Zhengyu Liu, Jingliang Duan, Wenxuan Wang et al.

This paper proposes an off-line algorithm, called Recurrent Model Predictive Control (RMPC), to solve general nonlinear finite-horizon optimal control problems. Unlike traditional Model Predictive Control (MPC) algorithms, it can make full use of the current computing resources and adaptively select the longest model prediction horizon. Our algorithm employs a recurrent function to approximate the optimal policy, which maps the system states and reference values directly to the control inputs. The number of prediction steps is equal to the number of recurrent cycles of the learned policy function. With an arbitrary initial policy function, the proposed RMPC algorithm can converge to the optimal policy by directly minimizing the designed loss function. We further prove the convergence and optimality of the RMPC algorithm thorough Bellman optimality principle, and demonstrate its generality and efficiency using two numerical examples.