Robotics Research Hub
EVPeriscope: Extended Perception across Aerial and Ground Vehicles with Event-based Propeller Tracking

EVPeriscope: Extended Perception across Aerial and Ground Vehicles with Event-based Propeller Tracking

Dexter Ong, Vijay Kumar, Pratik Chaudhari · N/A · 2026

vision reinforcement-learning planning control
PDF arXiv Code (GitHub)

Framework

N/A

License

N/A

Stars

N/A

Summary

Reliable relative localization between aerial and ground robots is a key requirement for tightly coordinated heterogeneous teams.

Abstract Summary

Reliable relative localization between aerial and ground robots is a key requirement for tightly coordinated heterogeneous teams. This can be difficult to do using conventional frame-based cameras and fiducial markers because they are sensitive to motion blur, lighting variations, and payload constraints. This paper presents EVPeriscope, an event-based perception system that enables detection, localization and control of a quadrotor using an upward-facing event camera on a ground robot by detecting the high-frequency visual signature of its propellers. This system allows the quadrotor to function as an extended perception system for the ground robot when onboard sensors exhibit degradation or occlusion. We demonstrate the capabilities of this marsupial ground-aerial system via experiments in challenging field conditions with wind speeds of up to 15 mph, in both daylight and at night. We show that the system supports localization and closed-loop navigation through dense foliage where the ground robot's sensors are occluded. Our control system for the quadrotor operates at 200 Hz entirely with onboard sensing and computation. More details and experiment videos can be found on the project page: https://ongdexter.github.io/evperiscope.

Key Points

  • Reliable relative localization between aerial and ground robots is a key requirement for tightly coordinated heterogeneous teams.
  • This can be difficult to do using conventional frame-based cameras and fiducial markers because they are sensitive to motion blur, lighting variations, and payload constraints.
  • This paper presents EVPeriscope, an event-based perception system that enables detection, localization and control of a quadrotor using an upward-facing event camera on a ground robot by detecting the high-frequency visual signature of its propellers.
  • This system allows the quadrotor to function as an extended perception system for the ground robot when onboard sensors exhibit degradation or occlusion.
  • We demonstrate the capabilities of this marsupial ground-aerial system via experiments in challenging field conditions with wind speeds of up to 15 mph, in both daylight and at night.

Method

The EVPeriscope system consists of an event-based propeller detection and tracking pipeline, quadrotor pose estimation module and UAV controller. The system diagram is shown in Fig. 2 . Event cameras produce sparse, high-temporal-resolution measurements that are inherently asynchronous and noisy, making instantaneous frame-based detection unreliable.

Method — EVPeriscope: Extended Perception across Aerial and Ground Vehicles with Event-based Propeller Tracking
Figure 2 : EVPeriscope system diagram. The UGV-mounted event camera detects and tracks the UAV propellers from asynchronous events, clusters them into propeller centroids, and uses the known asymmetric quadrotor geometry to estimate the UAV pose. The estimated pose is then used by the UGV controller to command the UAV through velocity commands. UAV observations and state estimates are transmitted to the UGV as extended perception that can be used for UGV autonomy.

Experiments

Altitude Position (m ) / Attitude (deg) Error X Y Z Roll Pitch Yaw 0.5 0.014 $\pm$ 0.006 0.027 $\pm$ 0.007 0.017 $\pm$ 0.005 1.975 $\pm$ 0.915 1.894 $\pm$ 1.137 1.342$\pm$ 0.103 1.0 0.065 $\pm$ 0.029 0.086 $\pm$ 0.015 0.023 $\pm$ 0.014 2.250 $\pm$ 1.856 1.970 $\pm$ 1.522 1.611 $\pm$ 0.155 2.0 0.084 $\pm$ 0.015 0.125 $\pm$ 0.024 0.129 $\pm$ 0.019 2.744 $\pm$ 2.419 5.162 $\pm$ 3.645 1.944 $\pm$ 0.320 4.0 0.142 $\pm$ 0.040 0.434 $\pm$ 0.035 0.493 $\pm$ 0.032 4.248 $\pm$ 3.131 9.432 $\pm$ 9.344 4.752 $\pm$ 0.576 6.0 0.364 $\pm$ 0.084 0.546 $\pm$ 0....

Experiments — EVPeriscope: Extended Perception across Aerial and Ground Vehicles with Event-based Propeller Tracking
Figure 3 : System hardware configuration. EVPeriscope (left) consists of a custom-built quadrotor (upper right), and a Unitree Go2-W with a custom sensor stack (lower right). The core sensors of the system include the ZED Mini on the UAV for perception and state estimation, and the iniVation DVXplorer Micro event camera on the UGV for propeller tracking. A ZED Mini, Ouster OS0-128 and ZED-F9P GPS module on the UGV are also used for baseline comparisons. A custom docking system supports carrying and landing the UAV.

Sources and Demonstrations

Figures are reproduced from Ong et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.

Share

Related Papers

Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think
arXiv preprint

Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

Xvyuan Liu, Jianjie Fang, Chen Gao et al.

Planners built on visual world models commonly score each predicted outcome by its distance to the encoded goal image. We show that this target can limit control even with exact dynamics and globally optimal short-horizon search: reaching a goal may require actions that initially move away from it.

vision reinforcement-learning planning control human-robot-interaction benchmark
PDF Intermediate
Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics
arXiv preprint

Autonomous Droplet Navigation via Model-Based Reinforcement Learning: Zero-Shot Transfer and Emergent Dynamics

Rajneesh Anand, Mayuresh V. Kothare

Self-driving laboratories (SDLs) are transforming chemical and materials discovery through closed-loop automation, yet automated infrastructure for physical manipulation of soft, deformable matter remains beyond current robotic platforms.

manipulation vision reinforcement-learning planning control
Code PDF Intermediate
GitHub ★ —