Grantee Research Project Results
LAMA: Localization and Mapping Artificial Intelligence Application
EPA Contract Number: 68HERC24C0018Title: LAMA: Localization and Mapping Artificial Intelligence Application
Investigators: Batchko, Robert
Small Business: Holochip Corporation
EPA Contact: Richards, April
Phase: I
Project Period: December 1, 2023 through May 30, 2024
Project Amount: $100,000
RFA: Small Business Innovation Research (SBIR) - Phase I (2024) RFA Text | Recipients Lists
Research Category: Small Business Innovation Research (SBIR)
Description:
Project Summary
LAMA is a localization and mapping application for disaster areas which doesn’t require access to external data (i.e., GPS, Bluetooth, Wi-Fi). It runs on modern commercial mobile devices and enables the creation of simplified 2D & 3D schematics of the user’s surroundings, location within it, and the path they have taken, accurate to within an inch.
Innovation
Current mobile-device-based mapping tools rely on both internal device sensors and external data; however, external data sources are unreliable in disaster areas. Current tools create multiple small maps linked to external data for user location, making constant access to external data necessary. LAMA enables accurate mapping on mobile devices in large areas without external data by creating a single comprehensive map using advanced data storage methods derived from the gaming industry. Existing mobile mapping solutions are constrained by data storage limitations, restricting the area they can map due to reliance on device RAM. As maps grow and change dynamically during user movement, device RAM becomes a constraint. LAMA enables mapping of large areas by employing a video game industry-inspired memory storage approach. The captured map is partitioned into sections, with only those near the user stored in RAM, while other sections are stored on the hard drive, facilitating scanning of large structures.
Technical Feasibility
The program's technical risk is minimal, as it leverages established technologies across industries where Holochip holds substantial expertise. Mapping utilizes sensors, and SDKs like ARKit (iOS) and ARCore (Android) found in modern mobile devices. Our engineers, experienced in AR and VR device development, have a solid history working with this technology. Map partitioning and storage, crucial components, draw from mature practices extensively utilized in the gaming sector, with Holochip engineers having successfully implemented them in numerous AAA game titles.
Performance Compared to Current Technologies
| Localization Method | Approximate Accuracy | Effective Indoors in Disaster Areas |
| GPS | 16 ft | No |
| Cellular | 1600 ft | Yes |
| Bluetooth | 3 ft | No |
| Wifi | 3 ft | No |
| LAMA | <1 in | Yes |
Commercial Impact
LAMA will tap into the nearly $2 billion indoor mapping industry. Primary users are retailers, hospitals, and warehouses for which LAMA offers a range of value propositions including enhancing customer experience, augmenting safety and security, and reducing costs.
Potential for Environmental Impact
LAMA has a very limited potential for environmental impact as it is a purely software-based solution with little or no use of high-power consumption cloud services.
Progress and Final Reports:
SBIR Phase II:
LAMA: Localization and Mapping Artificial Intelligence ApplicationThe perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Conclusions drawn by the principal investigators have not been reviewed by the Agency.