An Integrated Open-Source Stack for Vision-Based Autonomous Navigation of Wheeled Rovers
An Integrated Open-Source Stack for Vision-Based Autonomous Navigation of Wheeled Rovers
This paper introduces an open-source ROS 2 stack designed for vision-based autonomous navigation of wheeled rovers. The system integrates perception using YOLOv8n, localization via RGB-D SLAM, kinematics-aware planning, and behavior-tree mission management to execute tasks like following arrows, reaching a target cone, and returning autonomously. Evaluated on a Jetson Orin NX, the detector achieves an [email protected] of 0.720 on 478 held-out images with a reported latency of 25 ms. The authors demonstrate successful indoor and outdoor missions but emphasize that further instrumented trials are required to fully quantify physical navigation errors and system reliability.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S2
Reported numbers
photo captures
478
View original evidence
estimation with RGB-D SLAM, wheel-inertial state estimation, kinematics-aware planning, behavior-tree mission management and STM32 actuation. Standard interfaces separate reusable autonomy from the hardware layer; a proportional path-following plugin supports low-speed rover motion. Public resources include software, configuration, a labeled dataset, trained weights and evaluation logs. On 478 held-out images, the de
Open source S3perception latency
25
View original evidence
tector achieves [email protected] of 0.720 under the Ultralytics evaluator and outperforms a classical OpenCV baseline under a shared evaluation protocol. The reported perception latency is 25 ms on a Jetson Orin NX. Three missions, one indoor and two outdoor, demonstrate marker-guided navigation and autonomous return without operator motion commands or reported collisions. Field results document integration failures and corre
Open source S4mAP score
0.72
View original evidence
tector achieves [email protected] of 0.720 under the Ultralytics evaluator and outperforms a classical OpenCV baseline under a shared evaluation protocol. The reported perception latency is 25 ms on a Jetson Orin NX. Three missions, one indoor and two outdoor, demonstrate marker-guided navigation and autonomous return without operator motion commands or reported collisions. Field results document integration failures and corre
Open source S4missions
3
Reported trials
View original evidence
tector achieves [email protected] of 0.720 under the Ultralytics evaluator and outperforms a classical OpenCV baseline under a shared evaluation protocol. The reported perception latency is 25 ms on a Jetson Orin NX. Three missions, one indoor and two outdoor, demonstrate marker-guided navigation and autonomous return without operator motion commands or reported collisions. Field results document integration failures and corre
Open source S4
- paper: not_reported
- weights: Reported pending Open source S3
- dataset: Reported pending Open source S3
- code: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
estimation with RGB-D SLAM, wheel-inertial state estimation, kinematics-aware planning, behavior-tree mission management and STM32 actuation. Standard interfaces separate reusable autonomy from the hardware layer; a proportional path-following plugin supports low-speed rover motion. Public resources include software, configuration, a labeled dataset, trained weights and evaluation logs. On 478 held-out images, the de
Open source S3
arXiv:2611.08100v1 Announce Type: new Abstract: Vision-based rover autonomy requires integrating perception, localization, planning and platform-specific control under limited sensing and computing resources. We present an open-source ROS 2 stack for following directional arrows, reaching a terminal cone and returning autonomously to the start. It connects YOLOv8n detection and geometric direction, range and bearing
Open source S2
tector achieves [email protected] of 0.720 under the Ultralytics evaluator and outperforms a classical OpenCV baseline under a shared evaluation protocol. The reported perception latency is 25 ms on a Jetson Orin NX. Three missions, one indoor and two outdoor, demonstrate marker-guided navigation and autonomous return without operator motion commands or reported collisions. Field results document integration failures and corre
Open source S4
ctive choices; repeated instrumented trials remain necessary to quantify physical navigation errors and reliability.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org