ref.bib

@article{tamp,
  title = {Integrated Task and Motion Planning},
  volume = {4},
  ISSN = {2573-5144},
  url = {http://dx.doi.org/10.1146/annurev-control-091420-084139},
  DOI = {10.1146/annurev-control-091420-084139},
  number = {1},
  journal = {Annual Review of Control,  Robotics,  and Autonomous Systems},
  publisher = {Annual Reviews},
  author = {Garrett,  Caelan Reed and Chitnis,  Rohan and Holladay,  Rachel and Kim,  Beomjoon and Silver,  Tom and Kaelbling,  Leslie Pack and Lozano-Pérez,  Tomás},
  year = {2021},
  month = may,
  pages = {265–293}
}

@misc{enhancing-interpret,
      title={Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach}, 
      author={Georgios Tziafas and Hamidreza Kasaei},
      year={2023},
      eprint={2210.00858},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2210.00858}, 
}

@inproceedings{learning-neuro-symbolic,
  title = {Learning Neuro-symbolic Programs for Language Guided Robot Manipulation},
  url = {http://dx.doi.org/10.1109/icra48891.2023.10160545},
  DOI = {10.1109/icra48891.2023.10160545},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  publisher = {IEEE},
  author = {K,  Namasivayam and Singh,  Himanshu and Bindal,  Vishal and Tuli,  Arnav and Agrawal,  Vishwajeet and Jain,  Rahul and Singla,  Parag and Paul,  Rohan},
  year = {2023},
  month = may,
  pages = {7973–7980}
}

@misc{cliport,
      title={CLIPort: What and Where Pathways for Robotic Manipulation}, 
      author={Mohit Shridhar and Lucas Manuelli and Dieter Fox},
      year={2021},
      eprint={2109.12098},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2109.12098}, 
}

@misc{code-as-symbolic-planner,
      title={Code-as-Symbolic-Planner: Foundation Model-Based Robot Planning via Symbolic Code Generation}, 
      author={Yongchao Chen and Yilun Hao and Yang Zhang and Chuchu Fan},
      year={2025},
      eprint={2503.01700},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2503.01700}, 
}

@article{nsai,
  title = {Neuro-Symbolic AI for Advanced Signal and Image Processing: A Review of Recent Trends and Future Directions},
  url = {http://dx.doi.org/10.36227/techrxiv.174353019.93925639/v1},
  DOI = {10.36227/techrxiv.174353019.93925639/v1},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  author = {Fitas,  Ricardo},
  journal = {TechRxiv Preprint},
  year = {2025},
  month = apr 
}

@inproceedings{code-as-policies,
  title = {Code as Policies: Language Model Programs for Embodied Control},
  url = {http://dx.doi.org/10.1109/icra48891.2023.10160591},
  DOI = {10.1109/icra48891.2023.10160591},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  publisher = {IEEE},
  author = {Liang,  Jacky and Huang,  Wenlong and Xia,  Fei and Xu,  Peng and Hausman,  Karol and Ichter,  Brian and Florence,  Pete and Zeng,  Andy},
  year = {2023},
  month = may 
}

@article{text-2-motion,
  title = {Text2Motion: from natural language instructions to feasible plans},
  volume = {47},
  ISSN = {1573-7527},
  url = {http://dx.doi.org/10.1007/s10514-023-10131-7},
  DOI = {10.1007/s10514-023-10131-7},
  number = {8},
  journal = {Autonomous Robots},
  publisher = {Springer Science and Business Media LLC},
  author = {Lin,  Kevin and Agia,  Christopher and Migimatsu,  Toki and Pavone,  Marco and Bohg,  Jeannette},
  year = {2023},
  month = nov,
  pages = {1345–1365}
}

@inproceedings{plangenllm,
  title = {PlanGenLLMs: A Modern Survey of LLM Planning Capabilities},
  url = {http://dx.doi.org/10.18653/v1/2025.acl-long.958},
  DOI = {10.18653/v1/2025.acl-long.958},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  publisher = {Association for Computational Linguistics},
  author = {Wei,  Hui and Zhang,  Zihao and He,  Shenghua and Xia,  Tian and Pan,  Shijia and Liu,  Fei},
  year = {2025},
  pages = {19497–19521}
}

@misc{huggingface_vlms_2024,
  author       = {Merve and Edward Beeching},
  title        = {Vision Language Models Explained},
  year         = {2024},
  url          = {https://huggingface.co/blog/vlms},
  note         = {Accessed: 2025-08-23}
}

@misc{pddl,
  author = {Adam Green},
  title = {What is Planning Domain Definition Language (PDDL)?},
  url = {https://planning.wiki/guide/whatis/pddl},
  note = {Accessed: 2025-08-23}
}

@misc{hycodepolicy,
      title={HyCodePolicy: Hybrid Language Controllers for Multimodal Monitoring and Decision in Embodied Agents}, 
      author={Yibin Liu and Zhixuan Liang and Zanxin Chen and Tianxing Chen and Mengkang Hu and Wanxi Dong and Congsheng Xu and Zhaoming Han and Yusen Qin and Yao Mu},
      year={2025},
      eprint={2508.02629},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2508.02629}, 
}

@misc{audere,
      title={AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMs}, 
      author={Yue Meng and Fei Chen and Yongchao Chen and Chuchu Fan},
      year={2025},
      eprint={2504.03015},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2504.03015}, 
}

@manual{urarm,
  title        = {User manual – UR10e e-Series – SW 5.13},
  author       = {{Universal Robots A/S}},
  organization = {Universal Robots},
  year         = {2025},
  note         = {Available at: \url{https://www.universal-robots.com/download/}}
}

@inbook{ai-in-image-processing,
  title = {Advances in Artificial Intelligence for Image Processing: Techniques,  Applications,  and Optimization},
  ISBN = {9781668486207},
  ISSN = {2327-042X},
  url = {http://dx.doi.org/10.4018/978-1-6684-8618-4.ch006},
  DOI = {10.4018/978-1-6684-8618-4.ch006},
  booktitle = {Handbook of Research on Thrust Technologies’ Effect on Image Processing},
  publisher = {IGI Global},
  author = {Boopathi,  Sampath and Pandey,  Binay Kumar and Pandey,  Digvijay},
  year = {2023},
  month = jun,
  pages = {73–95}
}

@article{optimizatoin-and-motion-planning,
  title = {A Survey of Optimization-Based Task and Motion Planning: From Classical to Learning Approaches},
  volume = {30},
  ISSN = {1941-014X},
  url = {http://dx.doi.org/10.1109/TMECH.2024.3452509},
  DOI = {10.1109/tmech.2024.3452509},
  number = {4},
  journal = {IEEE/ASME Transactions on Mechatronics},
  publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
  author = {Zhao,  Zhigen and Cheng,  Shuo and Ding,  Yan and Zhou,  Ziyi and Zhang,  Shiqi and Xu,  Danfei and Zhao,  Ye},
  year = {2025},
  month = aug,
  pages = {2799–2825}
}

@article{recent-trends-in-tamp,
  title = {Recent Trends in Task and Motion Planning for Robotics: A Survey},
  volume = {55},
  ISSN = {1557-7341},
  url = {http://dx.doi.org/10.1145/3583136},
  DOI = {10.1145/3583136},
  number = {13s},
  journal = {ACM Computing Surveys},
  publisher = {Association for Computing Machinery (ACM)},
  author = {Guo,  Huihui and Wu,  Fan and Qin,  Yunchuan and Li,  Ruihui and Li,  Keqin and Li,  Kenli},
  year = {2023},
  month = jul,
  pages = {1–36}
}

@article{eval-application-challenges-llms,
  title = {Benchmark Evaluations,  Applications,  and Challenges of Large Vision Language Models: A Survey},
  url = {http://dx.doi.org/10.32388/GXR68Q},
  DOI = {10.32388/gxr68q},
  publisher = {Qeios Ltd},
  author = {Li,  Zongxia and Wu,  Xiyang and Du,  Hongyang and Nghiem,  Huy and Shi,  Guangyao},
  year = {2025},
  month = jan 
}

@inproceedings{llm-as-planning-formalizers,
  title = {LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models},
  url = {http://dx.doi.org/10.18653/v1/2025.findings-acl.1291},
  DOI = {10.18653/v1/2025.findings-acl.1291},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2025},
  publisher = {Association for Computational Linguistics},
  author = {Tantakoun,  Marcus and Muise,  Christian and Zhu,  Xiaodan},
  year = {2025},
  pages = {25167–25188}
}

@inproceedings{ns-vqa,
  title={Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding},
  author={Kexin Yi and Jiajun Wu and Chuang Gan and Antonio Torralba and Pushmeet Kohli and Joshua B. Tenenbaum},
  booktitle={Neural Information Processing Systems},
  year={2018},
  url={https://api.semanticscholar.org/CorpusID:52919654}
}

@misc{transporter,
      title={Transporter Networks: Rearranging the Visual World for Robotic Manipulation}, 
      author={Andy Zeng and Pete Florence and Jonathan Tompson and Stefan Welker and Jonathan Chien and Maria Attarian and Travis Armstrong and Ivan Krasin and Dan Duong and Ayzaan Wahid and Vikas Sindhwani and Johnny Lee},
      year={2022},
      eprint={2010.14406},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2010.14406}, 
}

@article{human-language-understanding,
    author = {Manning, Christopher D.},
    title = {Human Language Understanding \& Reasoning},
    journal = {Daedalus},
    volume = {151},
    number = {2},
    pages = {127-138},
    year = {2022},
    month = {05},
    abstract = {The last decade has yielded dramatic and quite surprising breakthroughs in natural
          language processing through the use of simple artificial neural network computations,
          replicated on a very large scale and trained over exceedingly large amounts of data. The
          resulting pretrained language models, such as BERT and GPT-3, have provided a powerful
          universal language understanding and generation base, which can easily be adapted to many
          understanding, writing, and reasoning tasks. These models show the first inklings of a
          more general form of artificial intelligence, which may lead to powerful foundation models
          in domains of sensory experience beyond just language.},
    issn = {0011-5266},
    doi = {10.1162/daed_a_01905},
    url = {https://doi.org/10.1162/daed\_a\_01905},
    eprint = {https://direct.mit.edu/daed/article-pdf/151/2/127/2060607/daed\_a\_01905.pdf},
}

@inproceedings{attention-is-all-you-need,
 author = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \L ukasz and Polosukhin, Illia},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Attention is All you Need},
 url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf},
 volume = {30},
 year = {2017}
}

@inproceedings{pddl-1.2,
  title={PDDL-the planning domain definition language},
  author={Drew McDermott and Malik Ghallab and Adele E. Howe and Craig A. Knoblock and Ashwin Ram and Manuela M. Veloso and Daniel S. Weld and David E. Wilkins},
  year={1998},
  url={https://api.semanticscholar.org/CorpusID:59656859}
}

@misc{hrm,
      title={Hierarchical Reasoning Model}, 
      author={Guan Wang and Jin Li and Yuhao Sun and Xing Chen and Changling Liu and Yue Wu and Meng Lu and Sen Song and Yasin Abbasi Yadkori},
      year={2025},
      eprint={2506.21734},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2506.21734}, 
}

@misc{multi,
  doi = {10.48550/ARXIV.2410.00822},
  url = {https://arxiv.org/abs/2410.00822},
  author = {Hu,  Jiliang and Li,  Zuchao and Wang,  Ping and Ai,  Haojun and Zhang,  Lefei and Zhao,  Hai},
  keywords = {Sound (cs.SD),  Computation and Language (cs.CL),  Audio and Speech Processing (eess.AS),  FOS: Computer and information sciences,  FOS: Computer and information sciences,  FOS: Electrical engineering,  electronic engineering,  information engineering,  FOS: Electrical engineering,  electronic engineering,  information engineering},
  title = {VHASR: A Multimodal Speech Recognition System With Vision Hotwords},
  publisher = {arXiv},
  year = {2024},
  copyright = {arXiv.org perpetual,  non-exclusive license}
}

@misc{vla,
      title={Vision-Language-Action Models: Concepts, Progress, Applications and Challenges}, 
      author={Ranjan Sapkota and Yang Cao and Konstantinos I. Roumeliotis and Manoj Karkee},
      year={2025},
      eprint={2505.04769},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2505.04769}, 
}

@misc{vla-in-robot,
      title={Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey}, 
      author={Rui Shao and Wei Li and Lingsen Zhang and Renshan Zhang and Zhiyang Liu and Ran Chen and Liqiang Nie},
      year={2025},
      eprint={2508.13073},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2508.13073}, 
}

@misc{ros-plan,
  author       = {KCL Planning Group},
  title        = {ROSPlan Documentation},
  year         = {2025},
  url          = {https://kcl-planning.github.io/ROSPlan/documentation/},
  note         = {Accessed: 2025-09-15}
}

@misc{urarm-ros2,
  author       = {Universal Robots},
  title        = {Universal Robots ROS2 Driver},
  year         = {2023},
  howpublished = {\url{https://github.com/UniversalRobots/Universal_Robots_ROS2_Driver}},
  note         = {Accessed: 2025-09-12}
}

@misc{segment-anything-2023,
  title={Segment Anything},
  author={Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick},
  year={2023},
  eprint={2304.02643},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2304.02643},
}

@misc{tlac-2025,
  title={TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification},
  author={Ans Munir and Faisal Z. Qureshi and Muhammad Haris Khan and Mohsen Ali},
  year={2025},
  eprint={2503.12206},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2503.12206},
}

@misc{hanwen2024_grasp,
  title={6-DoF Grasp Detection in Clutter with Enhanced Receptive Field and Graspable Balance Sampling},
  author={Hanwen Wang and Ying Zhang and Yunlong Wang and Jian Li},
  year={2024},
  eprint={2407.01209},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2407.01209},
}

@article{scene_seg,
  title={Semantic Scene Segmentation for Robotics},
  author={Juana Valeria Hurtado and Abhinav Valada},
  journal={arXiv preprint},
  year={2024},
  eprint={2401.07589},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2401.07589},
}

@misc{moveit-doc,
  author       = {PickNik Robotics},
  title        = {MoveIt2 Concepts Documentation},
  year         = {2025},
  url          = {https://moveit.picknik.ai/main/doc/concepts/concepts.html},
  note         = {Accessed: 2025-09-15}
}

@misc{moveit2,
  author       = {Elephant Robotics},
  title        = {MoveIt2 Development Guide (ROS2)},
  year         = {2025},
  url          = {https://docs.elephantrobotics.com/docs/mycobot_280_ar_en/3-FunctionsAndApplications/6.developmentGuide/ROS/12.2-ROS2/12.2.5-Moveit2/#introduction-to-moveit2},
  note         = {Accessed: 2025-09-15}
}

@article{smith2015voice,
  title={Voice-controlled robotic systems: A review},
  author={Smith, J. and Doe, A.},
  journal={Journal of Robotics},
  volume={23},
  number={4},
  pages={123-135},
  year={2015}
}

@article{tada2020robust,
  title={Robust understanding of robot-directed speech commands using sequence to sequence with noise injection},
  author={Tada, Masashi and Hagiwara, Y. and Tanaka, H. and Taniguchi, T.},
  journal={Frontiers in Robotics and AI},
  volume={6},
  pages={144},
  year={2020},
  doi={10.3389/frobt.2019.00144}
}

@article{gupta2025speech,
  title={Speech Recognition-Based Wireless Control System for Mobile Robotics: Design, Implementation, and Analysis},
  author={Gupta, Prashant and Mamodiya, Devendra Kumar and Al-Gburi, Hameed},
  journal={Automation},
  volume={6},
  number={3},
  pages={25},
  year={2025},
  doi={10.3390/automation6030025}
}

@inproceedings{yu2020vlas,
  title={VLAS: Vision-language-action model with speech instructions for customized robot manipulation},
  author={Yu, J. and Zhang, X.},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2020},
  url={https://openreview.net/forum?id=H1xWz1rKPH}
}

@article{liu2021multimodal,
  title={Multimodal speech recognition for robot manipulation: A survey},
  author={Liu, Y. and Wang, Z. and Li, X.},
  journal={IEEE Transactions on Robotics},
  volume={37},
  number={6},
  pages={1853-1872},
  year={2021}
}

@misc{iaarc2025_handover,
  title={Robot-to-human construction tool handover grasp prediction for 6-DOF robotic arm with parallel gripper},
  author={Anonymous},
  year={2025},
  note={Proceedings of the 42nd International Symposium on Automation and Robotics in Construction (ISARC)},
}

@misc{mogpe2022,
  title={MOGPE: Real-time and High-Precision Grasp Pose Estimation with Sim-to-Real Transfer},
  author={Anonymous},
  year={2022},
  eprint={2211.01048},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2211.01048}
}

@misc{grasping2023,
  title={Towards Precise Model-free Robotic Grasping with Sim-to-Real Transfer Learning},
  author={Anonymous},
  year={2023},
  eprint={2301.12249},
  archivePrefix={arXiv},
  primaryClass={cs.RO},
  url={https://arxiv.org/abs/2301.12249}
}

@misc{handover2024_fast,
  title={Fast and Comfortable Robot-to-Human Handover},
  author={Anonymous},
  year={2024},
  journal={Frontiers in Robotics and AI},
  volume={11},
  pages={11319614},
}

@misc{ros2-doc,
  title        = {ROS 2 Documentation: Humble},
  author       = {{Open Robotics}},
  year         = {2022},
  howpublished = {\url{https://docs.ros.org/en/humble/index.html}},
  note         = {Accessed: 2025-09-30}
}

@misc{coloseum,
      title={THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic
  Manipulation}, 
      author={Ranjay Krishna and Dieter Fox and Jiafei Duan and Wilbert Pumacay and Jesse Thomason and Ishika Singh},
      year={2024},
      eprint={2402.08191},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2402.08191}, 
}

@misc{ifra_link_attacher,
  author       = {IFRA Cranfield},
  title        = {IFRA Link Attacher Plugin for Gazebo},
  year         = {2022},
  howpublished = {\url{https://github.com/IFRA-Cranfield/IFRA_LinkAttacher}},
  note         = {Accessed: 2025-10-08},
}

@misc{cv_bridge,
  author       = {ROS Perception Group},
  title        = {cv\_bridge: ROS2 Package for Converting ROS Image Messages to OpenCV Images},
  year         = {2023},
  howpublished = {\url{https://github.com/ros-perception/vision_opencv}},
  note         = {Accessed: 2025-10-08},
}

@misc{gazebo,
  title        = {About Gazebo Sim},
  author       = {{Open Robotics / Gazebo Project}},
  howpublished = {\url{https://gazebosim.org/about}},
  year         = 2025,
  note         = {Accessed: 2025-10-13}
}

@misc{ur_ros2_driver,
  author       = {Universal Robots A/S},
  title        = {Universal Robots ROS2 Driver},
  year         = {2024},
  howpublished = {\url{https://github.com/UniversalRobots/Universal_Robots_ROS2_Driver}},
  note         = {Accessed: 2025-10-16}
}

@article{vcs,
  title = {A survey on Advancements in Voice Control Systems Enhancing Human-Computer Interaction through Speech Recognition and AI},
  volume = {0},
  ISSN = {3009-6022},
  url = {http://dx.doi.org/10.21608/erjsh.2025.334371.1373},
  DOI = {10.21608/erjsh.2025.334371.1373},
  number = {0},
  journal = {Engineering Research Journal (Shoubra)},
  publisher = {Egyptian Knowledge Bank},
  author = {El-Azazy,  Amir Ahmed Mohamed El-Had and El-kammar,  Raafat Abd-elfatah and Fawzy,  Ahmed Mohamed and Abd Elkader,  Hala Mohamed},
  year = {2025},
  month = jan,
  pages = {0–0}
}

@inproceedings{Chang2023,
  title     = {Multimodal Speech Recognition for Language-Guided Embodied Agents},
  author    = {Allen Chang and Xiaoyuan Zhu and Aarav Monga and Seoho Ahn and Tejas Srinivasan and Jesse Thomason},
  year      = {2023},
  booktitle = {Interspeech 2023},
  pages     = {1608--1612},
  doi       = {10.21437/Interspeech.2023-2262},
  issn      = {2958-1796},
}

@misc{assemblyai_docs,
  title        = {AssemblyAI API Documentation},
  howpublished = {\url{https://www.assemblyai.com/docs}},
  note         = {Accessed: 2025-10-22}
}

@misc{langchain-docs,
title = {LangChain Overview},
author = {{LangChain Team}},
year = {2025},
howpublished = {\url{https://docs.langchain.com/oss/python/langchain/overview}}
,
note = {Accessed on 13 November 2025}
}

@misc{the-fast-downward-planning-system,
      title={The Fast Downward Planning System}, 
      author={M. Helmert},
      year={2011},
      eprint={1109.6051},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/1109.6051}, 
}

@misc{fast-downward-website,
  author       = {Malte Helmert and Jendrik Seipp and others},
  title        = {Fast Downward: A Planning System},
  year         = {2025},
  howpublished = {\url{https://www.fast-downward.org/latest/}},
  note         = {Accessed: 2025-11-13}
}



// Vision BenchMark References
@article{kirillov2023segment,
  title={Segment Anything},
  author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and White, Spencer and Berg, Alexander and et al.},
  journal={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year={2023}
}

@misc{padilla2021metrics,
  title={Metrics for Object Detection},
  author={Padilla, Rafael and Netto, Sergio and da Silva, Eduardo},
  year={2021},
  howpublished={\url{https://github.com/rafaelpadilla/Object-Detection-Metrics}},
  note={Accessed: 2025-11-16}
}

@article{radford2021clip,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  author={Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela et al.},
  journal={ICML},
  year={2021}
}

@misc{openai_clip,
  author       = {OpenAI},
  title        = {CLIP Model Card},
  year         = {2021},
  howpublished = {\url{https://github.com/openai/CLIP}},
  note         = {Accessed: 2025-11-16}
}

@inproceedings{fang2020graspnet,
  title={GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping},
  author={Fang, Hao-Shu and Wang, Chenxi and Gou, Mingqi and Lu, Cewu},
  booktitle={CVPR},
  year={2020}
}

@article{wu2024grasping,
  title={Generative Grasping: Diffusion-Based Grasp Proposal for 6-DoF Robots},
  author={Wu, Zhen and Liang, Bowen and Sun, Yuan and Zhang, Qifeng},
  journal={RA-L},
  year={2024}
}

@article{daxberger2025mmspatial,
  title={Multimodal Spatial Understanding for Embodied AI},
  author={Daxberger, Erik and Hwang, Vincent and Li, Shang and others},
  journal={Transactions on Machine Learning Research},
  year={2025}
}

@inproceedings{zhao2023vsd,
  title={VSD: Visual Spatial Reasoning Benchmark for 3D Scenes},
  author={Zhao, Yichen and Xu, Jin and Liao, Zhi and others},
  booktitle={NeurIPS},
  year={2023}
}

@inproceedings{yin2021learning,
  title={Learning to Recover 3D Scene Geometry from RGB-D},
  author={Yin, Wei and Zhang, Jianming and Xie, Jin and others},
  booktitle={CVPR},
  year={2021}
}

@inproceedings{teed2020raft3d,
  title={RAFT-3D: Scene Flow Using Rigid-Motion Embeddings},
  author={Teed, Zachary and Deng, Jia},
  booktitle={CVPR},
  year={2020}
}

@misc{diehl,
      title={Automated Generation of Robotic Planning Domains from Observations}, 
      author={Maximilian Diehl and Chris Paxton and Karinne Ramirez-Amaro},
      year={2021},
      eprint={2105.13604},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2105.13604}, 
}

@article{planowl, title={PlanOwl: Automated PDDL Files Generation from OWL
Ontologies and Visual Language Models}, volume={7}, url={https://ojs.aaai.org/index.php/AAAI-SS/article/view/36944}, DOI={10.1609/aaaiss.v7i1.36944}, abstractNote={Automated task planning traditionally relies on manually generated domain models, creating bottlenecks in scalability and requiring extensive domain expertise. This paper presents a novel framework to automate the process of generating Planning Domain Definition Language (PDDL) domains and problem files by integrating Web Ontology Language (OWL) ontologies with Visual Language Models (VLMs). Our approach leverages the rich semantic structure of OWL ontologies to systematically define domain classes, predicates, and actions, while VLMs ground abstract ontological concepts in concrete visual observations—automating the generation of instance‑specific planning problems. The proposed framework transforms ontological knowledge into PDDL domain files through a mapping algorithm that preserves semantic relationships and logical constraints. The VLM performs visual scene analysis to identify relevant objects, attributes, and spatial configurations for generating initial states, while natural language instructions are used to derive goal states.
We evaluate the framework across multiple planning domains, demonstrating that it generates syntactically correct and semantically coherent PDDL domain and problem files directly from OWL ontologies, camera images, and natural language inputs. The resulting files are comparable in quality to those manually generated by planning experts and outperform previous automated systems in terms of semantic fidelity and adaptability.}, number={1}, journal={Proceedings of the AAAI Symposium Series}, author={Adamik, Mark and Forte, Paolo}, year={2025}, month={Nov.}, pages={634-643} }

@INPROCEEDINGS{ontology,
  author={Zhao, Jingyun and Vogel-Heuser, Birgit and Ao, Jicong and Wu, Yansong and Zhang, Liding and Hartl, Fandi and Hujo, Dominik and Bing, Zhenshan and Wu, Fan and Knoll, Alois and Haddadin, Sami and Vojanec, Bernd and Markert, Timo and Kraft, André},
  booktitle={2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, 
  title={Ontology Based AI Planning and Scheduling for Robotic Assembly}, 
  year={2024},
  volume={},
  number={},
  pages={9855-9862},
  keywords={Robotic assembly;Job shop scheduling;Production planning;Production;Ontologies;Dynamic scheduling;Throughput;Planning;Assembly;Smart manufacturing},
  doi={10.1109/IROS58592.2024.10802295}}

@inproceedings{mbse,
   title={Model-Based Workflow for the Automated Generation of PDDL Descriptions},
   volume={25},
   url={http://dx.doi.org/10.1109/ETFA61755.2024.10710982},
   DOI={10.1109/etfa61755.2024.10710982},
   booktitle={2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)},
   publisher={IEEE},
   author={Nabizada, Hamied and Jeleniewski, Tom and Gehlhoff, Felix and Fay, Alexander},
   year={2024},
   month=sep, pages={01–04} }

@MISC{hoebert,
  title     = "Automatic ontology-based plan generation for an industrial
               robotics system",
  author    = "Hoebert, Timon and Lepuschitz, Wilfried and Merdan, Munir",
  publisher = "Verlag der Technischen Universit{\"a}t Graz",
  year      =  2020
}

@misc{vilain,
      title={Vision-Language Interpreter for Robot Task Planning}, 
      author={Keisuke Shirai and Cristian C. Beltran-Hernandez and Masashi Hamaya and Atsushi Hashimoto and Shohei Tanaka and Kento Kawaharazuka and Kazutoshi Tanaka and Yoshitaka Ushiku and Shinsuke Mori},
      year={2024},
      eprint={2311.00967},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2311.00967}, 
}

@misc{image2pddl,
      title={Planning with Vision-Language Models and a Use Case in Robot-Assisted Teaching}, 
      author={Xuzhe Dang and Lada Kudláčková and Stefan Edelkamp},
      year={2025},
      eprint={2501.17665},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2501.17665}, 
}

@misc{llm+p,
      title={LLM+P: Empowering Large Language Models with Optimal Planning Proficiency}, 
      author={Bo Liu and Yuqian Jiang and Xiaohan Zhang and Qiang Liu and Shiqi Zhang and Joydeep Biswas and Peter Stone},
      year={2023},
      eprint={2304.11477},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2304.11477}, 
}

@misc{pddl-instruct,
      title={Teaching LLMs to Plan: Logical Chain-of-Thought Instruction Tuning for Symbolic Planning}, 
      author={Pulkit Verma and Ngoc La and Anthony Favier and Swaroop Mishra and Julie A. Shah},
      year={2025},
      eprint={2509.13351},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2509.13351}, 
}

@misc{verigraph,
      title={VeriGraph: Scene Graphs for Execution Verifiable Robot Planning}, 
      author={Daniel Ekpo and Mara Levy and Saksham Suri and Chuong Huynh and Abhinav Shrivastava},
      year={2024},
      eprint={2411.10446},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2411.10446}, 
}

@misc{sayplan,
      title={SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning}, 
      author={Krishan Rana and Jesse Haviland and Sourav Garg and Jad Abou-Chakra and Ian Reid and Niko Suenderhauf},
      year={2023},
      eprint={2307.06135},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2307.06135}, 
}

@misc{pddllm,
      title={One Demo Is All It Takes: Planning Domain Derivation with LLMs from A Single Demonstration}, 
      author={Jinbang Huang and Yixin Xiao and Zhanguang Zhang and Mark Coates and Jianye Hao and Yingxue Zhang},
      year={2026},
      eprint={2505.18382},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2505.18382}, 
}

@misc{unidomain,
      title={Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning}, 
      author={Haoming Ye and Yunxiao Xiao and Cewu Lu and Panpan Cai},
      year={2025},
      eprint={2507.21545},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2507.21545}, 
}


@Article{spca,
AUTHOR = {Pesjak, Drejc and Žabkar, Jure},
TITLE = {Robot Planning via LLM Proposals and Symbolic Verification},
JOURNAL = {Machine Learning and Knowledge Extraction},
VOLUME = {8},
YEAR = {2026},
NUMBER = {1},
ARTICLE-NUMBER = {22},
URL = {https://www.mdpi.com/2504-4990/8/1/22},
ISSN = {2504-4990},
ABSTRACT = {Planning in robotics represents an ongoing research challenge, as it requires the integration of sensing, reasoning, and execution. Although large language models (LLMs) provide a high degree of flexibility in planning, they often introduce hallucinated goals and actions and consequently lack the formal reliability of deterministic methods. In this paper, we address this limitation by proposing a hybrid Sense–Plan–Code–Act (SPCA) framework that combines perception, LLM-based reasoning, and symbolic planning. Within the proposed approach, sensory information is first transformed into a symbolic description of the world in Planning Domain Definition Language (PDDL) using an LLM. A heuristic planner is then used to generate a valid plan, which is subsequently converted to code by a second LLM. The generated code is first validated syntactically through compilation and then semantically in simulation. When errors are detected, local corrections can be applied and the process is repeated as necessary. The proposed method is evaluated in the OpenAI Gym MiniGrid reinforcement learning environment and in a Gazebo simulation on a UR5 robotic arm using a curriculum of tasks with increasing complexity. The system successfully completes approximately 71–75% of tasks across environments with a relatively low number of simulation iterations.},
DOI = {10.3390/make8010022}
}

@misc{llm-domain-generators,
      title={Large Language Models as Planning Domain Generators}, 
      author={James Oswald and Kavitha Srinivas and Harsha Kokel and Junkyu Lee and Michael Katz and Shirin Sohrabi},
      year={2024},
      eprint={2405.06650},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2405.06650}, 
}

@misc{ur-driver-issue,
  author       = {{Universal Robots ROS Driver Contributors}},
  title        = {Issue \#756: Motion execution problem in Universal Robots ROS2 Driver},
  year         = {2024},
  howpublished = {\url{https://github.com/UniversalRobots/Universal_Robots_ROS_Driver/issues/756}},
  note         = {Accessed: 2026-03-10}
}

@misc{urscript-docs,
  title        = {Develop with URScript},
  author       = {{Universal Robots}},
  year         = {2026},
  url          = {https://www.universal-robots.com/developer/urscript/},
  note         = {Accessed: 2026-03-12}
}

@manual{urscript-manual,
  title        = {The URScript Programming Language for e-Series and UR-Series},
  author       = {{Universal Robots A/S}},
  year         = {2025},
  url          = {https://www.universal-robots.com/download/manuals-e-seriesur-series/script/script-manual-e-series-and-ur-series-sw-517/}
}

@misc{urscript-overview,
  title        = {URScript Programming Overview},
  author       = {{Universal Robots}},
  year         = {2025},
  note         = {Programming language documentation for Universal Robots manipulators}
}

@misc{coqui-tts,
  title        = {TTS: A deep learning toolkit for Text-to-Speech generation},
  author       = {{Coqui.ai Contributors and Erogol}},
  year         = {2023},
  howpublished = {\url{https://github.com/coqui-ai/TTS}},
  note         = {GitHub repository. Accessed: 2026-03-18},
  license      = {MPL-2.0},
  doi          = {10.5281/zenodo.3950839}
}

@misc{bird,
title={Blocksworld Revisited: Learning and Reasoning to Generate Event-Sequences from Image Pairs},
author={Tejas Gokhale and Shailaja Sampat and Zhiyuan Fang and Yezhou Yang and Chitta Baral},
year={2019},
eprint={1905.12042},
archivePrefix={arXiv},
primaryClass={cs.CV} }