Guided airdrop parafoil systems depend on GPS for localization and landing. In some scenarios, GPS may be unreliable (jammed, spoofed, or disabled), or unavailable (indoor, or extraterrestrial environments). In the context of guided parafoils, landing locations for each system must be pre-programmed manually with global coordinates, which may be inaccurate or outdated, and offer no in-flight adaptability. Parafoil systems in particular have constrained motion, communication, and on-board computation and storage capabilities, and must operate in harsh conditions. These constraints necessitate a comprehensive approach to address the fundamental limitations of these systems when GPS cannot be used reliably. A novel and minimalist approach to visual navigation and multi-agent communication using semantic machine learning classification and geometric constraints is introduced. This approach enables localization and landing site identification for multiple communicating parafoil systems deployed in GPS-denied environments.
| Identifer | oai:union.ndltd.org:bu.edu/oai:open.bu.edu:2144/19500 |
| Date | 05 November 2016 |
| Creators | Chiel, Benjamin S. |
| Source Sets | Boston University |
| Language | en_US |
| Detected Language | English |
| Type | Thesis/Dissertation |
Page generated in 0.0019 seconds