E-Navi: Environmental Adaptive Navigation for UAVs on Resource Constrained Platforms

The ability to adapt to changing environments is crucial for the autonomous navigation systems of Unmanned Aerial Vehicles (UAVs). However, existing navigation systems adopt fixed execution configurations without considering environmental dynamics based on available computing resources, e.g., with a high execution frequency and task workload. This static approach causes rigid flight strategies and excessive computations, ultimately degrading flight performance or even leading to failures in UAVs. Despite the necessity for an adaptive system, dynamically adjusting workloads remains challenging, due to difficulties in quantifying environmental complexity and modeling the relationship between environment and system configuration. Aiming at adapting to dynamic environments, this paper proposes E-Navi, an environmental-adaptive navigation system for UAVs that dynamically adjusts task executions on the CPUs in response to environmental changes based on available computational resources. Specifically, the perception-planning pipeline of UAVs navigation system is redesigned through dynamic adaptation of mapping resolution and execution frequency, driven by the quantitative environmental complexity evaluations. In addition, E-Navi supports flexible deployment across hardware platforms with varying levels of computing capability. Extensive Hardware-In-the-Loop and real-world experiments demonstrate that the proposed system significantly outperforms the baseline method across various hardware platforms, achieving up to 53.9% navigation task workload reduction, up to 63.8% flight time savings, and delivering more stable velocity control.

💡 Research Summary

The autonomy of Unmanned Aerial Vehicles (UAVs) heavily relies on their ability to navigate through unpredictable and changing environments. However, a significant bottleneck in current navigation systems is the reliance on static execution configurations. Most existing frameworks operate with fixed task workloads and execution frequencies, regardless of whether the UAV is flying through an open field or a dense forest, or whether the onboard computer is a high-performance module or a resource-constrained embedded chip. This rigidity leads to two major issues: computational overload in complex environments, which can cause system failures, and unnecessary energy consumption in simple environments, which shortens mission duration.

To address these critical challenges, this paper introduces “E-Navi,” an innovative environmental-adaptive navigation system designed specifically for resource-constrained UAV platforms. The core philosophy of E-Navi is to break away from static processing by dynamically adjusting the computational intensity of the navigation pipeline in response to real-time environmental dynamics and available computing resources.

The technical cornerstone of E-Navi lies in its redesigned perception-planning pipeline. The system implements a dual-layered adaptation strategy: the dynamic adjustment of mapping resolution and the optimization of execution frequency. This is driven by a sophisticated mechanism that quantitatively evaluates environmental complexity. By quantifying how “difficult” the current environment is, E-Navi can intelligently decide when to use high-fidelity mapping and high-frequency control loops to ensure safety, and when to scale down these parameters to conserve power and CPU cycles.

Furthermore, E-Navi is engineered for high portability and flexibility. It supports seamless deployment across a wide spectrum of hardware platforms, ranging from powerful edge computing units to highly limited micro-controllers. This hardware-agnostic approach ensures that the navigation intelligence can be scaled according according to the specific capabilities of the drone’s onboard processor.

The effectiveness of E-Navi was rigorously validated through extensive Hardware-In-the-Loop (HITL) and real-world flight experiments. The results are remarkable, demonstrating that E-Navi can achieve up to a 53.9% reduction in navigation task workload compared to baseline methods. More importantly, this efficiency translates into a massive increase in operational endurance, with flight time savings of up to 63.8%. Beyond energy efficiency, the system also provides more stable velocity control, proving that reducing computational load does not come at the expense of flight stability. Ultimately, E-Navi provides a robust framework for the next generation of autonomous UAVs, enabling longer, safer, and more intelligent missions in diverse and challenging environments.