Real-Time Navigation for Autonomous Aerial Vehicles Using Video

2025-04-01

AI Summary

Real-time semantic navigation for resource-constrained autonomous aerial vehicles faces a fundamental trade-off between detection accuracy and energy efficiency, primarily due to the high computational cost of conventional 3D point cloud–based object detection. Method: This paper proposes a lightweight semantic-guided navigation framework that eliminates expensive 3D reconstruction and instead introduces a novel Markov Decision Process (MDP) model integrating semantic perception and navigation decision-making. It directly maps video-based semantic cues—such as traffic signs—into navigability criteria, enabled by a feature-engineered lightweight detector and online policy optimization for closed-loop control. Contribution/Results: Evaluated on simulation and hardware-in-the-loop (HIL) platforms, the framework achieves a 58% reduction in inference latency and a 42% decrease in system energy consumption compared to baseline methods, while maintaining navigation accuracy within a marginal drop of ≤2.3%. The approach significantly improves real-time performance and energy efficiency without compromising functional reliability.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Machine Learning: Hardware-aware ML

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Most applications in autonomous navigation using mounted cameras rely on the construction and processing of geometric 3D point clouds, which is an expensive process. However, there is another simpler way to make a space navigable quickly: to use semantic information (e.g., traffic signs) to guide the agent. However, detecting and acting on semantic information involves Computer Vision~(CV) algorithms such as object detection, which themselves are demanding for agents such as aerial drones with limited onboard resources. To solve this problem, we introduce a novel Markov Decision Process~(MDP) framework to reduce the workload of these CV approaches. We apply our proposed framework to both feature-based and neural-network-based object-detection tasks, using open-loop and closed-loop simulations as well as hardware-in-the-loop emulations. These holistic tests show significant benefits in energy consumption and speed with only a limited loss in accuracy compared to models based on static features and neural networks.

Problem

• Reducing computational cost of real-time aerial navigation
• Optimizing object detection for resource-limited drones
• Balancing accuracy and efficiency in autonomous flight

Innovation

• Uses semantic information for real-time navigation
• Introduces MDP framework to reduce CV workload
• Tests show energy and speed benefits