Objective. To develop, formalize, and evaluate a decentralized multi-agent system for realâtime traffic management in autonomous openâpit mining operations, aimed at minimizing truck idle time, preventing congestion and deadlocks, and increasing overall haulage efficiency. Methodology. The system is designed using a multiâagent paradigm where haul trucks, excavators,dumping points, and key infrastructure elements are modeled as autonomous agents. Task allocation is performed via a marketâbased Contract Net Protocol with bidding based on estimated time of arrival. Path planning employs an A* algorithm on a dynamic graph, while conflict resolution is achieved through a reservation mechanism managed by infrastructure agents. Reinforcement learning (Qâlearning) is integrated to allow truck agents to adapt their bidding strategies over time. The approach is validated through agentâbased simulations under normal, highâintensity, and disruption scenarios, and compared against a centralized firstâcome, firstâserved dispatch system. Results. Under normal operation, the multiâagent system reduced average truck idle time by 44%, cycle time by 17.5%, increased throughput by 21%, and lowered traffic conflict frequency by 66.5% compared to the baseline. In highâintensity traffic, it prevented congestion and deadlocks, maintaining smooth flow. During unexpected disruptions (excavator breakdown, road blockage), the system autonomously reâplanned routes and reassigned tasks within minutes, effectively isolating the impact and ensuring operational continuity. Scientific novelty. The novelty lies in the holistic integration of decentralized coordination, marketâbased task allocation, dynamic path reservation, and reinforcement learning within a unified multiâagent framework for realâtime traffic management in openâpit mining. This approach enables emergent selfâorganization, robust adaptation to dynamic conditions, and scalability beyond the capabilities of traditional centralized fleet management systems. Practical significance. The proposed system offers a scalable and resilient solution for autonomous haulage fleets, directly reducing operational costs through lower idle times and higher throughput, improving safety by preventing traffic conflicts, and enhancing resilience to equipment failures or route blockages. It provides a clear pathway for transitioning existing mines to fully autonomous, efficient, and safe operations. Keywords: multi-agent system, traffic management, open-pit mining, autonomous haulage, fleet management, reinforcement learning, Contract Net Protocol, path planning, conflict resolution, simulation.
Zongliang Zhang, Sherong Zhang, Zhiyong Zhao, Lei Yan · 6 authors
Improving the design efficiency of hydropower hub buildings and promoting the application of intelligence in engineering construction and operation management have been critical issues in hydropower engineering construction. The major challenges are mainly reflected in the difficulties of multidisciplinary collaboration and the inefficient coordination of work involving multiple parties. This paper proposes a building information modeling (BIM)-based technology system architecture for digital design, intelligent construction, and intelligent operation, which combines BIM technology with geographic information system (GIS), computer aided engineering (CAE), internet of things (IoT), artificial intelligence (AI), and other technologies. The proposed system includes a BIM-based multiprofessional forward collaborative design method, a BIM-based engineering construction management model, and a real-time safety analysis and evaluation technology system based on actual measured safety information and construction. The hydroelectrical engineering BIM (HydroBIM) comprehensive control platform is developed. In the planning and design stage, the platform enables the whole process and full-professional collaborative digital design. In the engineering construction management stage, it supports the whole process and all-round information management and control of contract, schedule, quality, safety, and investment. In the operation management stage, the platform facilitates the integrated management of engineering safety evaluation, early warning, and emergency plan based on monitoring data and the consistency criterion of positive and negative evaluation. The application of this technology in more than 20 engineering, has proven to improve the efficiency of design and analysis of hydropower hub buildings and the intelligence level of engineering construction and operation management, and overcome the difficulties of multi-professional collaboration in the design stage and low efficiency of multi-participant coordination in the construction stage.
Taiwan, like many other countries, often incentivizes private investors to participate in the construction of infrastructures for environmental protection. The build-operate-transfer (BOT) or build-operate-own (BOO) model of financing public infrastructure was introduced to Taiwan in the 1990s. Among them, the construction of incinerators to treat the municipal solid waste using the BOT/BOO model was quite a success in the beginning. With the socio-technical change of lifestyle and waste generation, the amount of amount of trash dropped dramatically. The policy failed eventually, however, because the government over-estimated the trash quantity and refrained from inter-municipality cooperation to treat trash efficiently. This failure triggered a rash of intense debates and legal disputes. In the case of the Taitung incinerator, the 26th incinerator located in southeastern Taiwan, the arbitration resulted in the government making significant compensation payments to the private sector. The finished construction was consequently converted into a âmothballed and pensioned offâ facility. This study applies in-depth interviews and literature review to discuss aspects contributing to the policy failure and proposes some possible remedial measures. Five aspects are summarized, namely, the administrative organizationâs rigid attitude, the irrationality of the BOT/BOO contracts, the loss of the spirit of BOO partnerships, the heavy financial burden on local government, and the abandonment of inter-municipality cooperation. The remedial measures for the policy failure are presented in the form of thorough policy evaluation, room for contract adjustments under the BOT/BOO model, encouragement of cross-boundary cooperation, and revision of the legal framework for implementing decentralization.
Private-ownership of roads in Nigeria is still at the deliberation stage. In other words roads (tarred and untarred) are owned by Federal, State and Local authorities in Nigeria. Most of these roads, however, share a common characteristic of being âunsafe at any speedâ, at any time of the day. This is as a result of the low quality of the road components, structures and patterns. For example, road surfaces are undulating and rough. Also, the poor standard of road infrastructure like guard railings/barriers; pavement marking and signs; illumination levels, traffic signals, horizontal/vertical alignment and sight lines contribute largely to the increasing carnage on Nigerian road network. This trend persists because authorities in Nigeria have practically relegated to the background regular road safety audit operations. This is an inevitable aspect of modern methods of road administration and management, which determines a number of traffic potentials concerning highway high collision locations; protection of errant vehicles from light poles, trees, ditches, replacement of damaged and missing signs, street lighting, capacity and level of service analysis. Finally, this paper suggests commissioning of a National Road Research Fund, with a view to developing an efficient road safety audit operational system. Also, the introduction of private initiatives and a Community-based Approach in road administration, as well as decentralization of road administration framework at all levels, will greatly help âengineer outâ potentially unsafe features across Nigerian roads, towards a better road traffic environment in the 21st century.