Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OIPP: Object-Adaptive Impact Point Predictor for Catching Diverse In-Flight Objects

Ngoc Huy Nguyen, Kazuki Shibata, Takamitsu Matsubara

TL;DR

A real-world dataset of 8,000 trajectories from 20 objects is constructed, providing a foundation for advancing in-flight object catching under complex aerodynamics and shows that improved early-stage prediction enhances catching success in simulation and demonstrates the effectiveness of the approach through real-robot experiments.

Abstract

In this study, we address the problem of in-flight object catching using a quadruped robot with a basket. Our objective is to accurately predict the impact point, defined as the object's landing position. This task poses two key challenges: the absence of public datasets capturing diverse objects under unsteady aerodynamics, which are essential for training reliable predictors; and the difficulty of accurate early-stage impact point prediction when trajectories appear similar across objects. To overcome these issues, we construct a real-world dataset of 8,000 trajectories from 20 objects, providing a foundation for advancing in-flight object catching under complex aerodynamics. We then propose the Object-Adaptive Impact Point Predictor (OIPP), consisting of two modules: (i) an Object-Adaptive Encoder (OAE) that extracts object-dependent representations from motion histories, and (ii) an Impact Point Predictor (IPP) that estimates the impact point from these representations. Two IPP variants are implemented: a Neural Acceleration Estimator (NAE)-based method that predicts trajectories and derives the impact point, and a Direct Point Estimator (DPE)-based method that directly outputs it. Experimental results show that our dataset is more diverse and complex than existing datasets, and that our method outperforms baselines on both 15 seen and 5 unseen objects. Furthermore, we show that improved early-stage prediction enhances catching success in simulation and demonstrate the effectiveness of our approach through real-robot experiments. The demonstration is available at https://sites.google.com/view/robot-catching-2025.

OIPP: Object-Adaptive Impact Point Predictor for Catching Diverse In-Flight Objects

TL;DR

A real-world dataset of 8,000 trajectories from 20 objects is constructed, providing a foundation for advancing in-flight object catching under complex aerodynamics and shows that improved early-stage prediction enhances catching success in simulation and demonstrates the effectiveness of the approach through real-robot experiments.

Abstract

In this study, we address the problem of in-flight object catching using a quadruped robot with a basket. Our objective is to accurately predict the impact point, defined as the object's landing position. This task poses two key challenges: the absence of public datasets capturing diverse objects under unsteady aerodynamics, which are essential for training reliable predictors; and the difficulty of accurate early-stage impact point prediction when trajectories appear similar across objects. To overcome these issues, we construct a real-world dataset of 8,000 trajectories from 20 objects, providing a foundation for advancing in-flight object catching under complex aerodynamics. We then propose the Object-Adaptive Impact Point Predictor (OIPP), consisting of two modules: (i) an Object-Adaptive Encoder (OAE) that extracts object-dependent representations from motion histories, and (ii) an Impact Point Predictor (IPP) that estimates the impact point from these representations. Two IPP variants are implemented: a Neural Acceleration Estimator (NAE)-based method that predicts trajectories and derives the impact point, and a Direct Point Estimator (DPE)-based method that directly outputs it. Experimental results show that our dataset is more diverse and complex than existing datasets, and that our method outperforms baselines on both 15 seen and 5 unseen objects. Furthermore, we show that improved early-stage prediction enhances catching success in simulation and demonstrate the effectiveness of our approach through real-robot experiments. The demonstration is available at https://sites.google.com/view/robot-catching-2025.

Paper Structure

This paper contains 32 sections, 8 equations, 9 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. Physics-based Approaches
  4. Regression-based Approaches
  5. Deep Learning-based Approaches
  6. Method
  7. OAE
  8. IPP
  9. Training Objective
  10. NAE-based Predictor
  11. DPE-based Predictor
  12. Experiment
  13. Dataset
  14. Compared Methods
  15. Training Setup
  16. ...and 17 more sections

Figures (9)

  • Figure 1: Catching diverse in-flight objects with complex aerodynamics using a quadruped robot
  • Figure 2: OIPP framework for catching diverse in-flight objects
  • Figure 3: 20 objects used for experiment
  • Figure 4: Dataset analysis for our dataset and the NAE dataset
  • Figure 5: Comparison of impact point errors. Statistically significant differences ($p < 0.05$) are denoted by ***.
  • ...and 4 more figures