# ActLoc: Learning to Localize on the Move via Active Viewpoint Selection

## TL;DR

ActLoc introduces an active viewpoint selection framework using an attention-based model to improve robot localization accuracy by choosing optimal camera orientations during navigation.

## Contribution

It presents a novel large-scale attention-based model for viewpoint prediction and active planning to enhance localization in robot navigation tasks.

## Key findings

- Achieves state-of-the-art in single-viewpoint selection
- Generalizes well to full trajectory planning
- Modular design applicable to various tasks

## Abstract

Reliable localization is critical for robot navigation, yet most existing systems implicitly assume that all viewing directions at a location are equally informative. In practice, localization becomes unreliable when the robot observes unmapped, ambiguous, or uninformative regions. To address this, we present ActLoc, an active viewpoint-aware planning framework for enhancing localization accuracy for general robot navigation tasks. At its core, ActLoc employs a largescale trained attention-based model for viewpoint selection. The model encodes a metric map and the camera poses used during map construction, and predicts localization accuracy across yaw and pitch directions at arbitrary 3D locations. These per-point accuracy distributions are incorporated into a path planner, enabling the robot to actively select camera orientations that maximize localization robustness while respecting task and motion constraints. ActLoc achieves stateof-the-art results on single-viewpoint selection and generalizes effectively to fulltrajectory planning. Its modular design makes it readily applicable to diverse robot navigation and inspection tasks.