In highly complex and uncertain geological conditions, drivers often operate TBM based on engineering experience, making it difficult to take multiple factors into account. The purpose of this paper is to propose a TBM intelligent decision-making system integrating rock information recognition, excavation performance prediction and operating parameter regulation, which can provide quantitative guidance for construction. Firstly, TBM field excavation data of 7023 tunnel rings were collected from the HJ tunnel in Northeast China, and three working conditions suitable for TBM were defined, namely soft rock strata, balanced strata and hard rock strata. Then, two multi-output prediction models based on tabular deep learning architecture were developed to accurately predict rock information and performance indicators, respectively. The mean relative root mean square error ( aRRMSE ), mean symmetrical mean absolute percentage error ( aSMAPE ), and mean correlation coefficient ( aCC ) of the two models were 0.3079, 0.0693, 0.9524 and 0.2257, 0.0733, 0.9740, respectively. The model performance is superior to classic algorithms such as RF, MLPNN, LightGBM, and SVR. Subsequently, Black-winged Kite algorithm is improved using Weighted Chebyshev Scalarization Strategy and Tent Chaotic Map Strategy, and the MOBK algorithm is proposed. A multi-objective optimization principle is further established, effectively considering tunneling efficiency, construction cost, engineering experience, and equipment safety. The optimization of parameters under three working conditions is realized. Compared with optimization algorithms such as MOPSO (Multi-Objective Particle Swarm Optimization) and NSGA-III (Non-dominated Sorting Genetic Algorithm III), The MOBK algorithm performed the best, and achieves excellent overall performance improvement (36.63%) with the minimum operating parameter adjustment (18.05%). Finally, intelligent decision-making system is constructed based on multi-output prediction model and multi-objective optimization method. The engineering application results show that the proposed system can automatically identify geological environment and provide recommended values of operating parameters in the actual excavation process.

Humans have long fantasized about self-driving vehicles for the sake of luxury, style, safety, and ease. Free road space detection for collision avoidance and path planning is a vital part of autonomous driving vehicles. Despite many researchers focusing on free road space detection, it remains an open and challenging problem for real-world applications. Many studies have attempted to fuse depth and LiDAR features with visual features to improve the overall performance of free road space detection. However, there is no guideline on how such features should be fused to complement the visual features. Additionally, most of the previously proposed methods are computationally expensive and not suitable for real-life applications. The main motivation of this study is to realize a lightweight model that addresses these problems without compromising performance. As the LiDAR and visual features exist in different spaces, the proposed method attempts to learn various transformation and fusion operations from LiDAR features to complement the visual features. To validate the performance of the proposed method, we conduct comprehensive experiments on prominent benchmark datasets. The results of the experiments reveal the superior performance of the proposed model while being lightweight. LRDNet ranks third overall (with a minor difference) and second among LiDAR-based methods on the KITTI road benchmark dataset. Furthermore, the proposed model is the least computationally expensive among state-of-the-art methods and can be considered an optimal trade-off between speed and accuracy.