524-24_SMART_Grant_Development_Cost_Etch__1___1_.xlsx
XLSX spreadsheet 1 MB Posted
- Attached to
- Competitive Selection OH|DOT52424-1
- Contract number
- DOT52424-1
- Issued by
- Ohio
About this file
This document is a detailed project plan for a SMART (Specific, Measurable, Achievable, Relevant, Time-bound) Grant development contract between Etch and the Oregon Department of Transportation (ODOT). The project involves collaboration with moove.ai and focuses on developing a Transportation Management Center (TMC) application with advanced incident detection and crash prediction capabilities, utilizing machine learning and real-time data processing technologies.
The contract is valued at $771,415 and spans from April 2024 to January 2025, broken down into 22 specific sprints. The scope of work includes developing a comprehensive system architecture, creating a decision support system, building machine learning models for safety predictions, setting up an event streaming platform (ESP) environment, and creating prototypes for incident detection and response. Key deliverables include a project workplan, data management plan, system architecture documentation, concept of operations (CONOPS), development of incident detection and crash prediction prototypes, integration of system components, proof of concept testing, and implementation reports. The project will utilize AWS hosting, Kubernetes infrastructure, and GitHub for code management, with the ultimate goal of providing ODOT with advanced predictive safety and incident management capabilities.
View the file
Other files
On GovTribe
Work with this file
- Download the original file
- Contacts named in this file
- Similar government files
- Ask GovTribe AI about this file
Text version
Sheet1
| Sprint Description | Date Range | |
| 1 | Begin to co-develop work plan, use cases, system architecture document, data sources, stakeholder requirements for TMC and alerts. | 4/01/24 – 4/15/24 |
| 2 | Finalize work plan and stakeholder requirements; Set up fresh ESP development environment (hosted by Etch). | 4/15/24 – 4/29/24 |
| 3 | Finish draft TMC application layout for stakeholder review. | 4/29/24 – 5/13/24 |
| 4 | Finalize all data source requirements. | 5/13/24 – 5/27/24 |
| 5 | Begin ingestion of Honda air bag deployment events and prediction data sources; finalize rules for alerts and mitigation. | 5/27/24 – 6/10/24 |
| 6 | Ingest Honda and prediction messages. | 6/10/24 – 6/24/24 |
| 7 | Finish first TMC application prototype using mock incidents and predictions; Iterate on prediction ML model. | 6/24/24 – 7/08/24 |
| 8 | Address stakeholder feedback on TMC UI; Iterate on prediction model. | 7/08/24 – 7/22/24 |
| 9 | Final integration of TMC application with development ESP environment; Iterate on prediction model. | 7/22/24 – 8/05/24 |
| 10 | Transmit real prediction and incident events to development ESP; Display events in TMC application. | 8/05/24 – 8/19/24 |
| 11 | Final implementation of Decision Support System for incidents and mitigations. | 8/19/24 – 9/02/24 |
| 12 | Integrate DSS messaging into alerts service. | 9/02/24 – 9/16/24 |
| 13 | Final implementation of alerts service. | 9/16/24 – 9/30/24 |
| 14 | Testing and Evaluation; Complete all integration scripts; Assist with Implementation Report. | 9/30/24 – 10/14/24 |
| 15 | Testing and Evaluation; Assist with Implementation Report. | 10/14/24 – 10/28/24 |
| 16 | Testing and Evaluation; Finish Draft Implementation Report. | 10/28/24 – 11/04/24 |
| 17 | Testing and Evaluation; Incorporate stakeholder feedback. | 11/04/24 – 11/18/24 |
| 18 | Assistance with Final ConOps; Incorporate final stakeholder feedback. | 11/18/24 – 12/02/24 |
| 19 | Assistance with Final ConOps; Deploy prototypes to ODOT. | 12/02/24 – 12/16/24 |
| 20 | Assistance with Final ConOps | 12/16/24 – 12/30/24 |
| 21 | Assistance with Final ConOps | 12/30/24 – 1/13/25 |
| 22 | Assistance with Final ConOps | 1/13/25 – 1/27/25 |
Cost
| Tasks | Deliverables | Cost |
| 1 | Project Workplan | $ 8,500 |
| Updated Project Management Plan (PMP) with Etch Project Workplan elements, including potential risks. | ||
| Initial stakeholder meetings, define requirements and establish sprint schedule for stakeholder demonstrations. | ||
| 2 | Data Source Selection | $ 10,200 |
| Updated Data Management Plan (DMP) with moove.ai data sources including origin, data use, and privacy, that is aligned with a data assessment coordinated with the stakeholders and Program Management team. | ||
| Sample data including realistic CSV mock of Honda airbag events. | ||
| 3 | Draft & Final System Architecture and Design | $ 36,200 |
| 3.1 | Data Transmission: ESP | |
| Document detailed schema of Kafka topics for ESP integration: incidents, safety predictions, and mitigations. | ||
| Documented data flows for the Program Management team. | ||
| 3.2 | Incident & Risk Response Rulebook | |
| Updated documentation based on the decision tree of planned responses for incident scenarios. | ||
| 3.3 | System Architecture Design | |
| System Architecture Document (sections added to the Program Management team deliverable). | ||
| Design specifications for ESP connector to send ODOT data to moove.ai for training, for implementors to build out in Phase 2 of the SMART grant if awarded. | ||
| 4 | Draft & Final Concept of Operations (CONOPS) | $ 6,400 |
| Updated CONOPS document consisting of design specifications, data requirements, performance measures, and testing plan. Etch will also provide details regarding operations and maintenance of the two pilot use cases | ||
| 5 | Development | $ 598,650 |
| 5.1 | Epic & User Story Creation | |
| Creation of epics and user stories for each use case. | ||
| Creation of sprint backlog (update Project Workplan). | ||
| 5.2 | Incident Detection Prototype Development | |
| Set up ESP environment for prototypes, hosted by Etch in AWS. | ||
| Data flowing through prototype ESP as new Kafka data topics for incident detections and identified responses, which will be available to ESP consumers and downstream systems. | ||
| Decision Support System microservice that uses the rulebook developed with the Program Management team in Task 3.2. | ||
| WebSocket server that provides streaming data to the TMC web application. | ||
| ESP connector to receive Honda air bag deployment events, initially consuming simulated mock airbag events. | ||
| Alerts microservice with a subscription management component. | ||
| All code located in the GitHub repository created for the project, with automated unit tests. | ||
| TMC web-based application providing a map, dashboard, and live incident visualization using simulated or real event data. | ||
| 5.3 | Crash Prediction Machine Learning Model Training & Live Predicting | |
| Machine learning model for safety score prediction. | ||
| An automated process to update the model. | ||
| Data flow through the prototype ESP Kafka data topics for roadway segment safety predictions (RoadIQ scores) and high-risk locations. | ||
| Visualization by ODOT and other stakeholders of model safety score output on a map. | ||
| New Kafka data topics for safety predictions and mitigations, which will be available to ESP consumers and downstream systems. | ||
| Machine Learning model that consumes real-time data, makes safety risk predictions, and writes them to ESP topics. | ||
| 5.4 | Integration of System Components | |
| Infrastructure as Code definitions (Kubernetes and Terraform) that describe the component’s required hardware resources and how they communicate in the integrated service mesh. | ||
| Crash prediction and proactive mitigation prototype system. | ||
| Incident detection and response prototype system. | ||
| 6 | Proof of Concept Testing | $ 59,865 |
| Integration test scripts that confirm accurate communication between components. | ||
| Work with the Program Management team to produce documentation of QA and testing procedures, so that the methodology is clear and automated tests can be performed. | ||
| 7 | Proof of Concept Evaluation | $ 25,600 |
| Assessment of test set accuracy for prediction of historic accident conditions using withheld training data, for incorporation into the Implementation Report. | ||
| Stakeholders test prototypes with real risk predictions and mock airbag data. | ||
| 8 | Develop a Plan for Production | $ 19,600 |
| A GitHub account with source code that has administrator access for ODOT. | ||
| Source code and test scripts in a set of GitHub repositories, with one for each system component and a single repository for integration tests. | ||
| Work with the Program Management team to document system maintenance. | ||
| Automated scripts to deploy the components into the ODOT Kubernetes cluster, following the practices of the current ODOT ESP scripts. | ||
| 9 | Draft & Final Implementation Reports | $ 6,400 |
| Updated Implementation Report based on testing results and performance metrics. |
Total Cost $ 771,415 image1.png
File details come from the government source that posted it. Updated .