Categories: Research

One Person Supervises 100 Drones

Revolutionizing Supervision: One Person, 100 Autonomous Vehicles

In a groundbreaking development, research conducted at Oregon State University has demonstrated that a single individual can effectively supervise a “swarm” of over 100 autonomous ground and aerial robots without overwhelming workload. This discovery marks a significant stride towards the efficient utilization of swarms across various domains, ranging from wildland firefighting to urban disaster response and package delivery.

Unlocking the Potential of Swarms

Julie A. Adams, from the OSU College of Engineering, emphasized the practicality of deploying delivery drones at scale, envisioning scenarios where a lone individual would be tasked with overseeing a large fleet of drones. While acknowledging that this study isn’t a definitive solution, Adams highlights its pivotal role in gathering essential data to advance such systems.

The OFFSET Program: Pioneering Research

This revelation stems from research conducted under the Defense Advanced Research Project Agency’s (DARPA) OFFSET program, aimed at developing Offensive Swarm-Enabled Tactics. Adams and her team, recipients of an OFFSET grant in 2017, spearheaded efforts to explore the feasibility of supervising swarms comprising up to 250 autonomous vehicles, including multi-rotor aerial drones and ground rovers, in complex urban environments.

Navigating Urban Challenges

The project’s focus extended to navigating challenging urban landscapes, where conventional communication methods like line-of-sight and satellite-based systems are hindered by buildings. Swarms deployed in these environments hold immense potential in enhancing safety measures for both military personnel and civilians.

Integration and System Development

Adams, serving as a co-principal investigator, played a pivotal role in integrating various facets of the swarm system, ranging from infrastructure development to swarm tactics and human-swarm teaming. The team’s efforts culminated in the creation of a user-friendly interface, empowering the designated “swarm commander” to oversee and coordinate the actions of the autonomous vehicles effectively.

Virtual Reality Interface: Empowering Commanders

Collaborating with Smart Information Flow Technologies, the team developed a cutting-edge virtual reality interface known as I3. This interface empowered swarm commanders to exert high-level control over the swarm’s actions, akin to a quarterback directing plays in football, without the need to manually operate each vehicle.

Field Testing and Performance Evaluation

Extensive field testing was conducted across multiple Department of Defense Combined Armed Collective Training Facilities, progressively introducing more vehicles with each exercise. The workload of swarm commanders was meticulously monitored through both self-assessment and physiological sensors, ensuring operational efficiency even under adverse conditions.

Promising Results and Future Implications

Despite occasional workload spikes, attributed to challenging environmental factors, swarm commanders consistently demonstrated the ability to successfully complete missions. These findings not only validate the viability of single-person supervision of swarms but also hold far-reaching implications for diverse applications beyond the scope of this project.

The remarkable achievement of supervising a swarm of autonomous vehicles with unparalleled efficiency signifies a paradigm shift in the realm of robotics and autonomous systems. With continued advancements in technology and research, the prospect of leveraging swarms for various societal benefits becomes increasingly tangible, heralding a future where human-robot collaboration reshapes countless industries.

Source: Science Daily


Grow your business with AI. Be an AI expert at your company in 5 mins per week! Free AI Newsletter

AI News

Recent Posts

Kling AI from Kuaishou Challenges OpenAI’s Sora

In February 2024, OpenAI introduced Sora, a video-generation model capable of creating one-minute-long, high-definition videos.…

6 months ago

Alibaba’s Qwen2 AI Model Surpasses Meta’s Llama 3

Alibaba Group Holding has unveiled Qwen2, the latest iteration of its open-source AI models, claiming…

6 months ago

Google Expands NotebookLM Globally with New Features

Google has rolled out a major update to its AI-powered research and writing assistant, NotebookLM,…

6 months ago

Stability AI’s New Model Generates Audio from Text

Stability AI, renowned for its revolutionary AI-powered art generator Stable Diffusion, now unveils a game-changing…

6 months ago

ElevenLabs Unveils AI Tool for Generating Sound Effects

ElevenLabs has unveiled its latest innovation: an AI tool capable of generating sound effects, short…

6 months ago

DuckDuckGo Introduces Secure AI Chat Portal

DuckDuckGo has introduced a revolutionary platform enabling users to engage with popular AI chatbots while…

6 months ago