Featured video: Coding for underwater robotics

2026-02-27 · Source: MIT News - Artificial intelligence · Field: Technology & Digital — Robotics & Autonomous Systems, Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

MIT Lincoln Laboratory intern Ivy Mahncke, a robotics engineering student from Olin College of Engineering, developed and tested algorithms for collaborative underwater navigation between human divers and robotic vehicles. Her work addressed the challenge of lacking traditional localization aids like GPS in underwater environments. Mahncke's internship, which began in 2025 with the Advanced Undersea Systems and Technology Group, involved troubleshooting the algorithm and culminated in field tests. She participated in operational underwater vehicle tests in the Atlantic Ocean, Charles River, and Lake Superior, acting as a lead field tester. This experience allowed her to see her software perform in real-world conditions, contributing significantly to an ambitious program's reach goals.

Key takeaway

For robotics engineers or students interested in autonomous systems, this work highlights the critical need for robust navigation solutions in GPS-denied environments. You should focus on developing and rigorously field-testing algorithms that enable collaborative human-robot operations, as real-world validation is paramount for success in challenging domains like underwater exploration.

Key insights

Underwater navigation algorithms can enable collaborative human-robot operations despite GPS limitations.

Principles

• Real-world field testing is crucial for algorithm validation.
• Trusting interns with lead roles fosters significant contributions.

Method

Develop and troubleshoot algorithms for collaborative human-robot underwater navigation, then conduct field tests on operational vehicles in diverse aquatic environments.

In practice

• Explore collaborative navigation for GPS-denied environments.
• Involve junior engineers in critical field testing roles.

Topics

• Underwater Robotics
• Navigation Algorithms
• MIT Lincoln Laboratory
• Robotics Engineering
• Field Testing

Best for: Robotics Engineer, AI Student, Research Scientist

Related on AIssential

• Human-machine teaming dives underwater — Combining human and robot strengths is crucial for effective underwater human-robot teaming in challenging environments.
• Online Navigation Planning for Long-term Autonomous Operation of Underwater Gliders — GLAE uses MCTS and a physics-informed simulator for robust, long-term autonomous underwater glider navigation.
• World Action Models give robots the ability to simulate consequences before they move — World Action Models enable robots to simulate action consequences, improving generalization and learning from unlabeled video data.
• NavTrust: Benchmarking Trustworthiness for Embodied Navigation — NavTrust benchmarks embodied navigation trustworthiness by systematically corrupting inputs to reveal robustness gaps.
• Towards End to End Motion Planning and Execution for Autonomous Underwater Vehicles Using Reinforcement Learning — An end-to-end hierarchical DRL system enables AUV navigation from raw sensor data to thruster commands.
• Engineering Reliable Autonomous Systems: Challenges and Solutions — The workshop identified a roadmap for reliable autonomous systems, distinguishing between existing academic solutions and areas needing further research.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by MIT News - Artificial intelligence.