Short answer

Prioritize sensor fusion strategies that balance accuracy with computational efficiency, especially for resource-constrained autonomous systems.

Field: Modelling
Source: Machines (2025)
Method: Experimental validation of a developed autonomous navigation system.
Evidence: Strong effect

Integrating RTK-GNSS with 2D LiDAR and a trajectory scoring algorithm enables precise path following and obstacle avoidance for low-speed electric vehicles without complex mapping. This modelling research insight is drawn from a 2025 study published in Machines. Using Experimental validation of a developed autonomous navigation system., researchers explored how this design variable affects real-world outcomes. The key design takeaway: Prioritize sensor fusion strategies that balance accuracy with computational efficiency, especially for resource-constrained autonomous systems.

Study

ModellingNew This WeekStrong effect

RTK-GNSS and LiDAR Fusion Achieves 7cm Lateral Deviation for Micro EVs at 10 km/h

Integrating RTK-GNSS with 2D LiDAR and a trajectory scoring algorithm enables precise path following and obstacle avoidance for low-speed electric vehicles without complex mapping.

Machines · 2025

Key Findings

01Average lateral deviation of 0.07 m at 10 km/h and 0.12 m at 15 km/h.
02Average heading deviation of approximately 3° at 10 km/h and 4° at 15 km/h.
03Safe obstacle avoidance with a minimum clearance of 1.2 m.
04Robustness against minor GNSS signal degradation without complex map building or inertial sensing.

Application

Design takeaway

Prioritize sensor fusion strategies that balance accuracy with computational efficiency, especially for resource-constrained autonomous systems.

How to apply

When designing autonomous systems for low-speed vehicles in predictable environments, consider combining RTK-GNSS for localization with a simple LiDAR for obstacle detection and a predictive algorithm for path planning.

Project actions

01Focus on the integration of different sensor data streams.
02Develop a clear algorithm for decision-making in obstacle avoidance.
03Consider the trade-offs between sensor cost, computational power, and navigation accuracy.

Method & Evidence

AimTo develop and validate a low-speed autonomous navigation system for micro electric vehicles using GNSS-RTK localization and real-time obstacle avoidance.

MethodExperimental validation of a developed autonomous navigation system.

ProcedureA Toyota COMS micro EV was retrofitted with RTK-GNSS and 2D LiDAR. A low-level control system for steering, acceleration, and braking was developed, alongside a high-level navigation controller for path following using GNSS data. A real-time obstacle avoidance system using a scored predicted trajectory algorithm was implemented. The system was tested on a closed-loop campus track.

ContextAutonomous navigation for low-speed micro electric vehicles in semi-structured environments (e.g., campuses, industrial parks).

Variables

IV["Vehicle speed","GNSS signal quality","Obstacle presence and position"]

DV["Lateral deviation","Heading deviation","Minimum clearance from obstacles","Successful obstacle avoidance"]

CV["Vehicle type (Toyota COMS micro EV)","Environment type (closed-loop campus track)","Sensor configuration (RTK-GNSS, 2D LiDAR)","Control system parameters"]

Strengths & Limitations

Strengths

+Demonstrates a practical, integrated system for autonomous navigation.
+Provides quantitative data on performance metrics (deviation, clearance).
+Addresses the need for low-cost, low-complexity solutions.

Limitations

The system's effectiveness is highly dependent on the quality and availability of GNSS signals. Testing was conducted on a closed track, which may not fully represent real-world complexities.

Reliability & validity

The study's reliability is supported by experimental validation on a real vehicle. Validity is strong for the specific context of low-speed navigation in semi-structured environments, but may be limited in more complex scenarios.

Think critically

How might the performance of this system be affected by dynamic obstacles or unpredictable pedestrian behavior?

Design Principles

"Intelligent sensor fusion and predictive trajectory scoring can achieve robust autonomous navigation without reliance on high-fidelity mapping or extensive sensor suites."

This approach offers a cost-effective and computationally lighter solution for autonomous navigation in micro electric vehicles, making autonomous features more accessible for applications with limited onboard resources. It demonstrates that robust navigation can be achieved by intelligently fusing readily available sensor data.

What This Means for Your Design

By combining a precise GPS system (RTK-GNSS) with a simple laser scanner (2D LiDAR) and a smart algorithm, a small electric car can drive itself accurately and avoid bumping into things, even if the GPS signal isn't perfect.

How to use in your project

1.Reference the paper when discussing sensor fusion techniques for autonomous systems.
2.Use the findings on lateral deviation and obstacle clearance as benchmarks for your own design project.

Add to My Project

Quick Cite

Paragraph starter

The integration of RTK-GNSS with 2D LiDAR, as demonstrated by Noomwongs et al. (2025), offers a practical approach to autonomous navigation for micro electric vehicles. Their system achieved precise path following with low lateral deviation and effective obstacle avoidance by employing a trajectory scoring algorithm, highlighting the potential for cost-effective autonomous solutions in constrained environments.

Source

Machines

GNSS-RTK-Based Navigation with Real-Time Obstacle Avoidance for Low-Speed Micro Electric Vehicles

journal · 2025

View source

Questions About This Research

What does the research say about rtk-gnss and lidar fusion achieves 7cm lateral deviation for micro evs at 10 km/h?: Prioritize sensor fusion strategies that balance accuracy with computational efficiency, especially for resource-constrained autonomous systems. Evidence: Machines (2025).
Why does "RTK-GNSS and LiDAR Fusion Achieves 7cm Lateral Deviation for Micro EVs at 10 km/h" matter for design?: This approach offers a cost-effective and computationally lighter solution for autonomous navigation in micro electric vehicles, making autonomous features more accessible for applications with limited onboard resources. It demonstrates that robust navigation can be achieved by intelligently fusing readily available sensor data.
How can designers apply this research?: Prioritize sensor fusion strategies that balance accuracy with computational efficiency, especially for resource-constrained autonomous systems.
What were the main findings?: Average lateral deviation of 0.07 m at 10 km/h and 0.12 m at 15 km/h.. Average heading deviation of approximately 3° at 10 km/h and 4° at 15 km/h.. Safe obstacle avoidance with a minimum clearance of 1.2 m.. Robustness against minor GNSS signal degradation without complex map building or inertial sensing.
What research method was used?: Experimental validation of a developed autonomous navigation system..
How strong is the evidence?: Evidence strength is rated Strong effect, based on a 2025 journal from Machines.
What should I do differently in my next project?: When designing autonomous systems for low-speed vehicles in predictable environments, consider combining RTK-GNSS for localization with a simple LiDAR for obstacle detection and a predictive algorithm for path planning.
What are the limitations?: Performance may degrade significantly with severe GNSS signal loss or in highly dynamic, complex environments. The system is optimized for low speeds.