Multiagent Approach for Real-Time Collision Avoidance and Path Replanning for Cranes
Bibliographic record
Abstract
Collisions on construction sites are one of the primary causes of fatal accidents. This paper proposes a multiagent-based approach to provide real-time support to the staff of construction projects. Collision avoidance is achieved by informing the crane operators about potential collisions and by providing motion replanning for crane operations. During the planning stage, a three-dimensional (3D) model of the static environment is created, and collision-free motion plans are generated by the agents for the cranes, considering engineering constraints and operation rules. During actual construction work, all mobile objects are tagged when entering the monitored area. A site state agent uses a real-time location system (RTLS), such as an ultra-wideband (UWB) system to collect location data, calculates the poses of the objects on site, and sends this information to other agents. By using this real-time updated information, agents can detect potential collisions and replan the path for the cranes for collision avoidance. A coordinator agent coordinates the movement of cranes by deciding their priorities. The site state agent, coordinator agent, and crane agents can communicate and negotiate with one another to make better decisions. The framework of the multiagent system is described in detail, and a prototype system is developed. Three case studies are used to verify and validate the proposed approach. The benefit of using the agent system is that real-time collision avoidance can be achieved by providing more awareness of the site situation and decision making through communication and negotiation between multiple agents, which results in safer and more productive work environment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".