# An Emergency Disposal Decision-making Method with Human--Machine Collaboration

arXiv: https://arxiv.org/abs/2305.18165 · HTML: https://mlsanity.com/paper/2305.18165/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 29 May 2023.

## Builds on (most cited first, 9 of 9)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces](https://mlsanity.com/paper/1709.10163/) (2017)
- [Trial without Error: Towards Safe Reinforcement Learning via Human Intervention](https://mlsanity.com/paper/1707.05173/) (2017)
- [simNet: Stepwise Image-Topic Merging Network for Generating Detailed and Comprehensive Image Captions](https://mlsanity.com/paper/1808.08732/) (2018)
- [A Review of Incident Prediction, Resource Allocation, and Dispatch Models for Emergency Management](https://mlsanity.com/paper/2006.04200/) (2020)
- [Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time](https://mlsanity.com/paper/1810.11545/) (2018)
- [Cycle-of-Learning for Autonomous Systems from Human Interaction](https://mlsanity.com/paper/1808.09572/) (2018)

## Abstract (arXiv)

Rapid developments in artificial intelligence technology have led to unmanned systems replacing human beings in many fields requiring high-precision predictions and decisions. In modern operational environments, all job plans are affected by emergency events such as equipment failures and resource shortages, making a quick resolution critical. The use of unmanned systems to assist decision-making can improve resolution efficiency, but their decision-making is not interpretable and may make the wrong decisions. Current unmanned systems require human supervision and control. Based on this, we propose a collaborative human--machine method for resolving unplanned events using two phases: task filtering and task scheduling. In the task filtering phase, we propose a human--machine collaborative decision-making algorithm for dynamic tasks. The GACRNN model is used to predict the state of the job nodes, locate the key nodes, and generate a machine-predicted resolution task list. A human decision-maker supervises the list in real time and modifies and confirms the machine-predicted list through the human--machine interface. In the task scheduling phase, we propose a scheduling algorithm that integrates human experience constraints. The steps to resolve an event are inserted into the normal job sequence to schedule the resolution. We propose several human--machine collaboration methods in each phase to generate steps to resolve an unplanned event while minimizing the impact on the original job plan.