Spatial-Temporal Agent-based Motion Prediction and Evasion Decision Engine (STAMPEDE)

The Personnel Recovery (PR) mission is vital to effectively plan and conduct military operations in overseas theaters. The military effort to prepare for and successfully execute the recovery of isolated personnel (IPs) is essential to maintaining force readiness, denying enemy critical intelligence, and protecting the lives of U.S. service members. The USAF is often a leader among services in integrating new PR resources and adopting new innovative technologies. Cutting-edge developments in Machine Learning (ML) and Artificial Intelligence (AI) have created an opportunity to advance current PR planning resources and operational PR support products. Deep Learning (DL) approaches are highly effective at identifying temporal and spatial patterns in geospatial data. Reinforcement Learning (RL) can discover successful behaviors and decisions in realistic military simulations.  If harnessed effectively, AI and ML technologies can equip PR planners, coordinators, and IPs with a significant technological advantage over their adversaries. However, new technologies are often tough to deploy at scale. Broad-based adoption is difficult across large military and government organizations. Human behavior is challenging to model. To meet these challenges, Machina Cognita Technologies (MCT) proposes the Spatial-Temporal Agent-based Motion Prediction and Evasion Decision Engine (STAMPEDE). STAMPEDE will be designed to provide users at each level of the joint PR C2 architecture with guidance through an enhanced suite of DL-powered planning and coordination aids. The STAMPEDE system will ingest a wide array of data sources that characterize PR scenarios. STAMPEDE will be compatible with LandSAR mobility model plugin data and incorporate new dynamic data sources. STAMPEDE will return IP location probability maps at sequenced time intervals back to decision support tools.  Accompanied by easily interpreted explanations, recommended evasion decisions that avoid capture will be output directly to PR planners and coordinators. STAMPEDE will enable PR planners and coordinators to identify exclusion zones that reduce SAR search areas and drive more efficient searches through spatial-temporal human motion pattern discovery. STAMPEDE’s IP evasion movement recommendations will guide AOR evasion plans of action (EPAs) and theater wide PR guidance using ML-powered prediction and recommendation tools. STAMPEDE will generate customized evasion planning and decision guidance tailored to specific threat scenarios, real-world geographically bounded locations, and individual IP mobility behaviors and circumstances. STAMPEDE’s evasion decision explanations will instill PR user trust in and drive greater PR user adoption of the system using intuitive ML explainability models. STAMPEDE will empower PR users to reduce operational costs and increase the likelihood of successful evasion, survival and recovery through ML model location predictions and evasion decisions recommendations.