Event-Based Visual Teach-and-Repeat via Fast Fourier-Domain Cross-Correlation

Gokul B. Nair; Alejandro Fontan; Michael Milford; Tobias Fischer

cs.ROSep 21, 2025

Event-Based Visual Teach-and-Repeat via Fast Fourier-Domain Cross-Correlation

Authors: Gokul B. Nair, Alejandro Fontan, Michael Milford, Tobias Fischer

Organizations: The authors are with the QUT Centre for Robotics, Faculty of Engineering, Queensland University of Technology, Brisbane, QLD Australia 4000

Abstract

Visual teach-and-repeat (VT&R) navigation enables robots to autonomously traverse previously demonstrated paths using visual feedback. We present a novel event-camera-based VT&R system. Our system formulates event-stream matching as frequency-domain cross-correlation, transforming spatial convolutions into efficient Fourier-space multiplications. By exploiting the binary structure of event frames and applying image compression techniques, we achieve a processing latency of just 2.88 ms, about 3.5 times faster than conventional camera-based baselines that are optimised for runtime efficiency. Experiments using a Prophesee EVK4 HD event camera mounted on an AgileX Scout Mini robot demonstrate successful autonomous navigation across 3000+ meters of indoor and outdoor trajectories in daytime and nighttime conditions. Our system maintains Cross-Track Errors (XTE) below 15 cm, demonstrating the practical viability of event-based perception for real-time VT&R navigation.

Figures & tables

Fig. 1: Event-based visual teach-and-repeat system overview. (a): The robot records event streams during the teach phase (left) and autonomously follows the trajectory during repeat (right) using Fast Fourier Transform (FFT)-based cross-correlation of accumulated event frames. (b): Cross-correlations lead to timely navigational corrections in the form of repeatedly updating goals. (c): Our system deployed on an AgileX Scout Mini with Prophesee EVK4 achieves ${\approx}$ 300 Hz correction rates throughout autonomous navigation.

Fig. 2: Pipeline. Left : In the teach phase, a topometric map is constructed while teleoperating the mobile robot. The map stores event frames along with corresponding robot poses derived from raw odometry at regular intervals of linear or angular displacement (Section III-B ). Left-Centre : In the repeat phase, as the robot retraces the teach trajectory using the stored poses, incoming event frames are matched with those in the topometric map via cross-correlation. This is performed by point-wise multiplication of image pairs in the Fourier domain (Section III-C2 ). Right-Centre : Correlation results yield lateral pixel offsets, which are converted to angular corrections and issued to the robot as updated goal poses (Section III-C3 ). Right : Along-path corrections are estimated by evaluating correlations across the search space (Section III-C4 ) and applied to the robot’s motion using Equation 12 .

Fig. 3: Experimental platform and environments. Top-left : AgileX Scout Mini robot with a front-mounted Prophesee EVK4 HD event camera and an onboard processing laptop. Top-right : Narrow spaces found in our indoor (top) and outdoor (bottom) trial scenarios. Bottom-left : Indoor trajectory visualized on a map from SLAM Toolbox [ 47 ] . Bottom-right : Example outdoor trajectory (223 m) over tiled and grass surfaces.

Category	Parameter	Value
EVK4 Biases	bias_diff_off & bias_diff_on	40
	bias_fo	-35
	bias_hpf & bias_refr	0
Event Frame	Fixed event count, $N$	$1\times 10^{5}$ events
	Event window stride, $M$	$1\times 10^{3}$ events
	Initial frame dimensions	1280 $\times$ 720

TABLE I: Parameters

Tr.

Len.

Odom-only

Dall’Osto et al. [ 12 ]

Nourizadeh et al. [ 11 ]

Event VT&R (Ours)

(m)

Indoor

9.85

\pm

13.94

0/1

6.08

\pm

6.06

6.40

\pm

6.24

6.91

\pm

6.80

3/3

4.58

\pm

3.17

4.80

\pm

3.82

4.14

\pm

4.03

3/3

6.96

\pm

6.83

6.36

\pm

5.54

5.68

\pm

4.83

3/3

100

6.98

\pm

10.84

0/1

6.53

\pm

6.38

12.88

\pm

12.07

6.89

\pm

5.98

3/3

9.84

\pm

10.95

8.05

\pm

5.18

8.98

\pm

8.11

3/3

8.69

\pm

7.52

7.68

\pm

7.88

8.82

\pm

9.25

3/3

200

7.03

\pm

9.19

0/1

7.51

\pm

7.31

11.79

\pm

12.45

6.93

\pm

7.13

3/3

12.93

\pm

11.14

11.40

\pm

10.11

9.67

\pm

9.15

3/3

10.94

\pm

8.83

8.57

\pm

6.63

8.66

\pm

7.32

3/3

Outd.

120

36.76

\pm

40.55

0/1

11.73

\pm

8.74

8.61

\pm

6.67

31.03

\pm

30.67

3/3

8.44

\pm

7.02

5.23

\pm

4.96

12.01

\pm

9.76

3/3

5.27

\pm

6.48

9.99

\pm

6.91

8.11

\pm

7.37

3/3

223

80.03

\pm

110.29

0/1

17.67

\pm

16.20

20.19

\pm

19.52

14.25

\pm

19.63

3/3

15.62

\pm

16.84

17.31

\pm

19.77

18.06

\pm

17.92

3/3

5.78

\pm

5.25

11.74

\pm

9.67

14.68

\pm

10.72

3/3

TABLE II: Comparison of navigation performance across indoor and outdoor trajectories for our approach (Ours), an odometry-only baseline, and RGB-based VT&R [ 12 , 11 ] . For each trajectory, the results are reported as the mean and standard deviation of the Cross-Track Error (XTE), in centimetres, for up to three repeated trials, along with the corresponding success rate (SR). The odometry-only results additionally include the travelled distance as a percentage of the full trajectory length (% Length). Our system achieves comparable performance with the RGB-based VT&R approaches [ 12 , 11 ] . Our method consistently completes the full trajectories in all repeats, achieving 100% success rate.

Fig. 4: Navigation performance across indoor and outdoor trajectories. Top row: Three indoor trajectories (left) and one outdoor trajectory (right). The blue paths denote the teach trajectories, the green paths show the repeat trajectories using our event-based correction, and the red paths indicate the odometry-only repeats. Both indoor and outdoor trajectories were estimated using LiDAR SLAM. Next to each map, failure cases of the odometry-only baseline are shown. In these examples, the green arrows indicate the direction the robot is expected to traverse for a successful repeat. Bottom row: Cross-Track Error (XTE) for our method (green) and the odometry-only baseline ( red ). Note that the odometry-only XTE grows unbounded, making the system prone to collisions and eventual failure.

Fig. 5: Event-Accumulation Strategies under Varying Linear Velocities. (Section V-C1 ) Left : Comparison of Repeat and corresponding Teach frames using fixed-time binning. Significant appearance divergence occurs during angular motion, leading to navigation failure. Center : Comparison of frames using fixed-event count binning (proposed) at the same location. The representations remain consistent despite the change in linear velocity (0.33 m/s vs. 1.00 m/s). Top-Right : When using fixed-time accumulation, repeats at $0.66$ and $1.00$ m/s fail for teach traverse taken at $0.33$ m/s. Bottom-Right : For our proposed fixed-event count strategy, all three repeat traverses are completed with 100% success rate.

Image Compression	Horizontal Concatenation	Time (ms)
$\times$	$\times$	26.90
$\checkmark$	$\times$	3.63
$\times$	$\checkmark$	17.19
$\checkmark$	$\checkmark$	2.34

TABLE III: Computational optimisations for image matching

Visual Navigation

Visual navigation enables robots and embodied agents to reach goals by interpreting camera images and acting in unfamiliar or changing environments.

See all 71 papers

Fast and Robust Teach-and-Repeat Navigation Using MixVPR Visual Place Recognition*
Oct 7, 2026Václav Truhlařík, Tomáš Pivoňka, Libor PřeučilRobot Navigation Embodied Navigation
Czech Institute of Informatics, Robotics and Cybernetics, Czech technical University in Prague, Jugosl´avsk´ych partyz´an˚u 1580/3, 160 00 Praha 6, Czech Republic · Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Karlovo n´amˇest´ı 13, 121 35 Praha 2, Czech Republic
DAPEVO: Deep Adaptive Patch Frame-Event Visual Odometry
Sep 25, 2026Luca Gandolfi, Simone Nascivera, Roberto Pellerito +3Visual Odometry RGB-Event Sensor Fusion
Robotics and Perception Group, University of Zurich, Switzerland · Bocconi University, Italy
Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation
Oct 27, 2026Dequan Ou, Austin Lopez, Quentin Missinne +2Robotics Simulation Event-Based Vision
All authors are with the Micro Air Vehicle Lab of the Faculty of Aerospace Engineering, Delft University of Technology, 2629 HS Delft, The Netherlands

Oct 7, 2026J/K move · Enter open · S save

Fast and Robust Teach-and-Repeat Navigation Using MixVPR Visual Place Recognition*

Václav Truhlařík, Tomáš Pivoňka, Libor Přeučil

Czech Institute of Informatics, Robotics and Cybernetics, Czech technical University in Prague, Jugosl´avsk´ych partyz´an˚u 1580/3, 160 00 Praha 6, Czech Republic · Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Karlovo n´amˇest´ı 13, 121 35 Praha 2, Czech Republic

Robot Navigation Embodied Navigation

Open paper AskPDF arXiv

Teach-and-repeat navigation systems employing advanced visual place recognition techniques for localization exhibit key attributes for long-term mobile robot navigation, such as the ability to operate in unstructured and dynamic environments. However, existing solutions based on deep-learning techniques are computationally demanding, limiting their applicability. This work introduces a novel and efficient teach-and-repeat system built on the modern visual place recognition method MixVPR. Real-world testing demonstrated its ability to operate both indoors and outdoors, achieving robustness and navigation precision comparable to other state-of-the-art systems. In addition, its lower hardware requirements make it suitable for a wide range of robotic platforms and practical applications.

Abstract

Visual Navigation

Explore similar work

Fast and Robust Teach-and-Repeat Navigation Using MixVPR Visual Place Recognition*

DAPEVO: Deep Adaptive Patch Frame-Event Visual Odometry

Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation