The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Explore, Approach, and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning
Abstract
Searching for objects and distinguishing task-relevant objects from others is a key requirement for service robots. We propose a reinforcement learning solution to the active visual object search problem. Our method successfully learns to explore the environment, to approach the target object, and to decide when to terminate the search as the target object has been found. We demonstrate the efficiency of our solution on a dataset of real-world images collected by a robot. Our approach outperforms state-space planning or other baseline search strategies, reaching a higher success rate in a shorter time. We also study individual subtasks of active visual object search. Although strong baselines exist for the subtasks, our RL solution outperforms them in the overall search task.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Our motion policy explicitly exploits the knowledge of the environment for the visibility modelling, instead other RL-based strategies [9], [10] implicitly encode such environment knowledge in a data-driven manner.”
From Unsupervised Active Visual Search With Monte Carlo Planning Under Uncertain Detections (2024) · cites this paper as [10]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 2×
“The cropped segment is processed by Inception-v3 [18] trained on ILSVRC [19], the output of which is fed into a FC layer with”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“The top branch produces y(1) t by first applying the region proposal network (RPN) from [17] to extract 300 bounding boxes of object proposals from the input image.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812 · cited 1×
“The top branch produces y(1) t by first applying the region proposal network (RPN) from [17] to extract 300 bounding boxes of object proposals from the input image.”
MethodRethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471 · cited 2×
“Our method extends the deep recurrent Q-network (DRQN) [5] to solve the visual object search problem.”
MethodReinforcement Learning: An Introduction
Johnson, J. D., Li, J., & Chen, Z. (2000) · Neurocomputing · doi:10.1016/s0925-2312(00)00324-6 · Cited by 8,414
Dueling Network Architectures for Deep Reinforcement Learning
Wang, Z., Schaul, T., Hessel, M., van Hasselt, H., Lanctot, M., & de Freitas, N. (2015) · arXiv · doi:10.48550/arxiv.1511.06581 · Cited by 3,300 · cited 1×
“For the policy module μ(st), we employ the dueling DQN approach [21], predicting the state values and action advantages.”
MethodTarget-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533 · cited 4×
“Recent advances in image understanding through deep convolutional neural networks allow high-dimensional image inputs in RL methods for visual object search [2], [3], [4].”
BackgroundMethodInfluentialDeep Recurrent Q-Learning for Partially Observable MDPs
Hausknecht, M., & Stone, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.06527 · Cited by 667 · cited 8×
“[2] evaluate memory extensions to the DRQN [5], using search environments within the Minecraft video game.”
MethodInfluential
Cited by
Liu, S., Tian, G., Shao, X., & Liu, S. (2022) · IEEE Transactions on Robotics · doi:10.1109/tro.2022.3191745 · Cited by 23
“Jan et al. investigated an RL solution with long short-term memory (LSTM), which can actively end the AOD task [19].”
BackgroundPOMP: Pomcp-based Online Motion Planning for active visual search in indoor environments
Wang, Y., Giuliari, F., Berra, R., Castellini, A., Bue, A. D., Farinelli, A., Cristani, M., & Setti, F. (2020) · British Machine Vision Conference (BMVC) · doi:10.5244/c.34.190 · Cited by 15
POMP++: Pomcp-based Active Visual Search in unknown indoor environments
Giuliari, F., Castellini, A., Berra, R., Bue, A. D., Farinelli, A., Cristani, M., Setti, F., & Wang, Y. (2021) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros51168.2021.9635866 · Cited by 18
“deep recurrent Q-network (DRQN), with visual semantics, by either feeding deep visual embeddings to policy learning networks [1], [2] or obtaining 3D scene”
BackgroundMethodInfluentialLiu, S., Tian, G., Cui, Y., & Shao, X. (2022) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.2200109 · Cited by 12
Efficient Object Search Through Probability-Based Viewpoint Selection
Hernandez, A. C., Derner, E., Gómez, C., Barber, R., & Babuška, R. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9340989 · Cited by 11
“In [13], an object proposal method is applied to create a hypothesis about the target object location.”
BackgroundMethod
Metadata
- Authors
- Schmid, J. F., Lauri, M., & Frintrop, S.
- Affiliations
- Universität Hamburg (DE)
- Venue
- 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2019-11
- Pages
- 5008-5013
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W3003289302
- Cited by
- 12
- References
- 23
- Citations by year
- 2025: 1 · 2024: 4 · 2023: 1 · 2022: 2 · 2021: 2 · 2020: 2
- FWCI
- 0.57
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- deep reinforcement learning, service robots, exploration, search termination, robot vision
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Explore, Approach, and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning. https://app.cochat.ai/papers/10.1109/iros40897.2019.8967805
- The paper
- Schmid, J. F., Lauri, M., & Frintrop, S. (2019). Explore, Approach, and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). https://doi.org/10.1109/iros40897.2019.8967805
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.