The paper presents an efficient LiDAR-trajectory affinity model for autonomous vehicle orchestration, called the Box Data Association Inflation (BDAI) model. The proposed system uses a Bayesian approach to assess each target's object state and trajectory without noise. The BDAI model and box object filter are designed to reduce computational complexity and improve tracking accuracy. The system is evaluated on the NuScenes dataset and a lab dataset, achieving 58.09% tracking accuracy and 71% mAP with 5 ms pre-processing time. The Jetson Xavier NX consumes 49.63% GPU and 9.37% average power and exhibits 25.32 ms latency compared to other approaches. The system trains a single pair frame in 169.71 ms with an affinity estimation time of 12.19 ms, track association time of 0.19 ms, and mATE of 0.245. The BDAI model is derived based on binomial expansion and is used to filter ambiguous detection responses during data association. The system is designed to handle extended objects with size, shape, direction, and position, and it is effective in tracking objects in real-time scenarios. The proposed system achieves a lower tracking error rate than state-of-the-art approaches due to the Bayesian approach used in the affinity model. The system is efficient in terms of computational complexity and resource usage, making it suitable for lightweight cyber-physical systems. The results show that the proposed method is effective in detecting and tracking objects in autonomous vehicle orchestration.The paper presents an efficient LiDAR-trajectory affinity model for autonomous vehicle orchestration, called the Box Data Association Inflation (BDAI) model. The proposed system uses a Bayesian approach to assess each target's object state and trajectory without noise. The BDAI model and box object filter are designed to reduce computational complexity and improve tracking accuracy. The system is evaluated on the NuScenes dataset and a lab dataset, achieving 58.09% tracking accuracy and 71% mAP with 5 ms pre-processing time. The Jetson Xavier NX consumes 49.63% GPU and 9.37% average power and exhibits 25.32 ms latency compared to other approaches. The system trains a single pair frame in 169.71 ms with an affinity estimation time of 12.19 ms, track association time of 0.19 ms, and mATE of 0.245. The BDAI model is derived based on binomial expansion and is used to filter ambiguous detection responses during data association. The system is designed to handle extended objects with size, shape, direction, and position, and it is effective in tracking objects in real-time scenarios. The proposed system achieves a lower tracking error rate than state-of-the-art approaches due to the Bayesian approach used in the affinity model. The system is efficient in terms of computational complexity and resource usage, making it suitable for lightweight cyber-physical systems. The results show that the proposed method is effective in detecting and tracking objects in autonomous vehicle orchestration.