Further Reading & Resources¶
Foundational reading¶
Books¶
-
Pfeifer, R. & Bongard, J. (2006). How the Body Shapes the Way We Think: A New View of Intelligence. MIT Press. The academic foundation for embodied intelligence — why physical interaction shapes cognition.
-
Sutton, R. & Barto, A. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. incompleteideas.net/book/the-book.html The foundational RL textbook. Essential for understanding how robot policies are trained in simulation.
-
Nikolenko, S. I. (2021). Synthetic Data for Deep Learning. Springer. Comprehensive treatment of synthetic data generation, domain randomization, and domain adaptation.
Papers¶
-
Brohan, A., et al. (2023). "RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control." arXiv:2307.15818 The paper that established VLAs as a paradigm.
-
Tobin, J., et al. (2017). "Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World." arXiv:1703.06907 The seminal domain randomization paper.
-
Ha, D. & Schmidhuber, J. (2018). "World Models." arXiv:1803.10122 The influential paper framing world models as learned environment simulators.
-
LeCun, Y. (2022). "A Path Towards Autonomous Machine Intelligence." openreview.net Yann LeCun's position paper on world models and the JEPA architecture.
-
Driess, D., et al. (2023). "PaLM-E: An Embodied Multimodal Language Model." arXiv:2303.03378 Demonstrating VLMs for embodied reasoning.
-
Zhao, W., et al. (2020). "Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey." arXiv:2009.13303 Comprehensive survey of sim-to-real techniques.
-
Sculley, D., et al. (2015). "Hidden Technical Debt in Machine Learning Systems." NeurIPS 2015. The foundational paper on ML operational challenges — relevant to understanding why MLOps matters.
NVIDIA ecosystem¶
Documentation¶
- NVIDIA Physical AI — Platform overview and vision
- NVIDIA Omniverse — Platform documentation
- Isaac Sim — Robotics simulation
- Isaac Lab — RL/IL training framework
- Cosmos Models — World foundation models
- GR00T — Humanoid robot foundation model
- NIMs — Inference microservices
- OpenUSD — Scene description standard
- Alliance for OpenUSD — Governance body
Developer resources¶
- NVIDIA Developer — SDKs, tools, tutorials
- NVIDIA Isaac Platform — Robotics platform overview
- build.nvidia.com — Try NIM APIs online
- NGC Catalog — Container images, models, Helm charts
- NVIDIA Cosmos Cookbook — Recipes for Cosmos model usage
GitHub repositories¶
Red Hat ecosystem¶
Documentation¶
- OpenShift Container Platform
- Red Hat OpenShift AI
- Red Hat OpenShift GitOps
- Red Hat ACM
- Single Node OpenShift
- MicroShift
- Compliance Operator
GPU on OpenShift¶
Upstream projects¶
- KServe — Model serving
- Kubeflow Pipelines — ML pipeline orchestration
- MLflow — Experiment tracking
- Argo CD — GitOps
- Strimzi — Kafka on Kubernetes
- Sigstore — Software signing
- MuJoCo — Physics engine
Standards and frameworks¶
- ISA/IEC 62443 — Industrial cybersecurity standard. isa.org
- ISO 23247 — Digital twin framework for manufacturing. iso.org
- NIST SP 800-82 Rev. 3 — Guide to OT Security. csrc.nist.gov
- DISA STIGs — Security Technical Implementation Guides. access.redhat.com
- SLSA — Supply-chain Levels for Software Artifacts. slsa.dev
- Industry 5.0 — EU research and innovation framework. ec.europa.eu
Open-source datasets¶
- Open X-Embodiment — Robot manipulation data from 22 embodiments. robotics-transformer-x.github.io
- DROID — Distributed Robot Interaction Dataset. droid-dataset.github.io
- BridgeData V2 — Large-scale robot manipulation dataset. rail-berkeley.github.io/bridgedata
Open-source VLA models¶
- OpenVLA — Open-source VLA based on Llama 2 + SigLIP. openvla.github.io
- Octo — General-purpose robot policy for fine-tuning. octo-models.github.io
- GR00T N1 — NVIDIA's humanoid foundation model. github.com/NVIDIA/Isaac-GR00T