AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies

TL;DR

AimBot introduces a lightweight visual augmentation that overlays spatial cues onto images to significantly enhance the learning and performance of visuomotor policies in robotic manipulation tasks.

Contribution

It presents AimBot, a simple, computationally efficient method for providing explicit spatial guidance through visual overlays, improving visuomotor policy effectiveness without altering existing models.

Findings

Improves visuomotor policy performance in simulation and real-world

Minimal computational overhead (<1 ms)

No changes needed to existing model architectures

Abstract

In this paper, we propose AimBot, a lightweight visual augmentation technique that provides explicit spatial cues to improve visuomotor policy learning in robotic manipulation. AimBot overlays shooting lines and scope reticles onto multi-view RGB images, offering auxiliary visual guidance that encodes the end-effector's state. The overlays are computed from depth images, camera extrinsics, and the current end-effector pose, explicitly conveying spatial relationships between the gripper and objects in the scene. AimBot incurs minimal computational overhead (less than 1 ms) and requires no changes to model architectures, as it simply replaces original RGB images with augmented counterparts. Despite its simplicity, our results show that AimBot consistently improves the performance of various visuomotor policies in both simulation and real-world settings, highlighting the benefits of spatially grounded visual feedback.