← Back ICRA 2026

Mixed-Type Query Selection for Robotic Scientific Data Collection

Ian C. Rankin, Thane Somers, Alivia M. Eng, Geoffrey A. Hollinger

PDF

AI summary

Key figure (auto-extracted from paper)

Combining rating and preference queries into a mixed-type selection strategy improves robotic reward learning and data collection performance over using either query type alone.

Human-Robot Collaboration Reward Learning Query Selection Robotic Data Collection Preference Learning Active Learning

Problem

Learning a robot’s reward function for scientific data collection typically relies on either rating or preference queries, but each has limitations and selecting the optimal type for a given situation is difficult without knowing the user’s error model.

Approach

The method dynamically selects between rating and preference queries by comparing their estimated alignment with the user’s true preferences, utilizing both a known-error model strategy and a heuristic approach for unknown error models.

Key results

Mixed-type selection with known error models outperforms single-type strategies across simulated users
Heuristic mixed strategy consistently beats worst-case single query types when error models are unknown
Successfully optimizes sampling plans for planetary science in-situ measurements
Validated on real-world drone-orthomosaic data from Mt. Hood

Why it matters

Enables more efficient and accurate human-in-the-loop robotic data collection for scientists operating in challenging or remote environments.

Abstract

We propose combining preference and rating query types into a mixed-type query selection to learn reward functions for robotic decision making to improve scientific data collection. Mixed-type query selection allows the scientist operating a robot to specify the robot’s tradeoffs and goals in terms of both rating, giving a score to one robot plan, and preferences, selecting a preferred plan to another plan. While previous methods have used active learning to allow the user to specify tradeoffs between objectives using rating and preferences individually, our proposed method considers using multiple query types. We assume a user responds to these queries with some noise on their true preferences. Online estimation of error model parameters is difficult; therefore, we show results with both a tuned known error model and a heuristic mixed-type query selection method. When the error model is known, we show performance increases using our mixed-type query selection versus using only ratings or only preferences. In the more realistic case with an unknown error model, we show our heuristic performs better than the worst case single query type in all cases we tested.

Index terms

Human-Robot Collaboration Motion and Path Planning Field Robots