Robotics papers

@robotics_papers
13 Followers
14 Following
53 Posts
Curated feed of interesting and novel robotics papers.
Robotics papersJan 8, 2025

Diminishing Return of Value Expansion Methods

Authors: Daniel Palenicek, Michael Lutter, João Carvalho, Daniel Dennert, Faran Ahmad, and Jan Peters Fellow

pre-print -> https://arxiv.org/abs/2412.20537

#rl #reinforcement_learning #modelbased_rl #value_expension

Diminishing Return of Value Expansion Methods

Model-based reinforcement learning aims to increase sample efficiency, but the accuracy of dynamics models and the resulting compounding errors are often seen as key limitations. This paper empirically investigates potential sample efficiency gains from improved dynamics models in model-based value expansion methods. Our study reveals two key findings when using oracle dynamics models to eliminate compounding errors. First, longer rollout horizons enhance sample efficiency, but the improvements quickly diminish with each additional expansion step. Second, increased model accuracy only marginally improves sample efficiency compared to learned models with identical horizons. These diminishing returns in sample efficiency are particularly noteworthy when compared to model-free value expansion methods. These model-free algorithms achieve comparable performance without the computational overhead. Our results suggest that the limitation of model-based value expansion methods cannot be attributed to model accuracy. Although higher accuracy is beneficial, even perfect models do not provide unrivaled sample efficiency. Therefore, the bottleneck exists elsewhere. These results challenge the common assumption that model accuracy is the primary constraint in model-based reinforcement learning.

arXiv.org
Robotics papersDec 10, 2024

Neo-FREE: Policy Composition Through Thousand Brains And Free Energy Optimization

Authors: Francesca Rossi, Émiland Garrabé, Giovanni Russo

pre-print -> https://arxiv.org/abs/2412.06636

code -> https://github.com/GIOVRUSSO/Control-Group-Code/tree/master/Neo-FREE

#robotics #control #optimal_control #movement_primitives

Neo-FREE: Policy Composition Through Thousand Brains And Free Energy Optimization

We consider the problem of optimally composing a set of primitives to tackle control tasks. To address this problem, we introduce Neo-FREE: a control architecture inspired by the Thousand Brains Theory and Free Energy Principle from cognitive sciences. In accordance with the neocortical (Neo) processes postulated by the Thousand Brains Theory, Neo-FREE consists of functional units returning control primitives. These are linearly combined by a gating mechanism that minimizes the variational free energy (FREE). The problem of finding the optimal primitives' weights is then recast as a finite-horizon optimal control problem, which is convex even when the cost is not and the environment is nonlinear, stochastic, non-stationary. The results yield an algorithm for primitives composition and the effectiveness of Neo-FREE is illustrated via in-silico and hardware experiments on an application involving robot navigation in an environment with obstacles.

arXiv.org
Robotics papersDec 5, 2024

Novel Magnetic Actuation Strategies for Precise Ferrofluid Marble Manipulation in Magnetic Digital Microfluidics: Position Control and Applications

Authors: Mohammad Hossein Sarkhosh, Mohammad Hassan Dabirzadeh, Mohamad Ali Bijarchi, Hossein Nejat Pishkenari

pre-print -> https://arxiv.org/abs/2412.02859

#robotics #control #manipulation #microfluidics

Novel Magnetic Actuation Strategies for Precise Ferrofluid Marble Manipulation in Magnetic Digital Microfluidics: Position Control and Applications

Precise manipulation of liquid marbles has significant potential in various applications such as lab-on-a-chip systems, drug delivery, and biotechnology and has been a challenge for researchers. Ferrofluid marble (FM) is a marble with a ferrofluid core that can easily be manipulated by a magnetic field. Although FMs have great potential for accurate positioning and manipulation, these marbles have not been precisely controlled in magnetic digital microfluidics, so far. In this study for the first time, a novel method of magnetic actuation is proposed using a pair of Helmholtz coils and permanent magnets. The governing equations for controlling the FM position are investigated, and it is shown that there are three different strategies for adjusting the applied magnetic force. Then, experiments are conducted to demonstrate the capability of the proposed method. To this aim, different magnetic setups are proposed for manipulating FMs. These setups are compared in terms of energy consumption and tracking ability across various frequencies. The study showcases several applications of precise FM position control, including controllable reciprocal positioning, simultaneous position control of two FMs, the transport of non-magnetic liquid marbles using the FMs, and sample extraction method from the liquid core of the FM.

arXiv.org
Robotics papersDec 5, 2024

Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification

Authors: Marzieh Mohammadi, Amir Salarpour

pre-print -> https://arxiv.org/abs/2412.03056
code (to come) -> https://github.com/asalarpour/Point_GN

#point_cloud #classification #positional_embedding #non_parametric

Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification

This paper introduces Point-GN, a novel non-parametric network for efficient and accurate 3D point cloud classification. Unlike conventional deep learning models that rely on a large number of trainable parameters, Point-GN leverages non-learnable components-specifically, Farthest Point Sampling (FPS), k-Nearest Neighbors (k-NN), and Gaussian Positional Encoding (GPE)-to extract both local and global geometric features. This design eliminates the need for additional training while maintaining high performance, making Point-GN particularly suited for real-time, resource-constrained applications. We evaluate Point-GN on two benchmark datasets, ModelNet40 and ScanObjectNN, achieving classification accuracies of 85.29% and 85.89%, respectively, while significantly reducing computational complexity. Point-GN outperforms existing non-parametric methods and matches the performance of fully trained models, all with zero learnable parameters. Our results demonstrate that Point-GN is a promising solution for 3D point cloud classification in practical, real-time environments.

arXiv.org
Robotics papersDec 4, 2024

From Instantaneous to Predictive Control: A More Intuitive and Tunable MPC Formulation for Robot Manipulators

Authors: Johan Ubbink, Ruan Viljoen, Erwin Aertbeliën, Wilm Decré, Joris De Schutter

pre-print -> https://arxiv.org/abs/2412.01597v1

#robotics #motion_control #mpc

From Instantaneous to Predictive Control: A More Intuitive and Tunable MPC Formulation for Robot Manipulators

Model predictive control (MPC) has become increasingly popular for the control of robot manipulators due to its improved performance compared to instantaneous control approaches. However, tuning these controllers remains a considerable hurdle. To address this hurdle, we propose a practical MPC formulation which retains the more interpretable tuning parameters of the instantaneous control approach while enhancing the performance through a prediction horizon. The formulation is motivated at hand of a simple example, highlighting the practical tuning challenges associated with typical MPC approaches and showing how the proposed formulation alleviates these challenges. Furthermore, the formulation is validated on a surface-following task, illustrating its applicability to industrially relevant scenarios. Although the research is presented in the context of robot manipulator control, we anticipate that the formulation is more broadly applicable.

arXiv.org
Robotics papersDec 3, 2024
Rust Weekly 🦀Dec 3, 2024

Show HN: Copper – Open-source robotics in Rust with deterministic log replay

https://github.com/copper-project/copper-rs/wiki/Copper-Release-Log

Discussions: https://discu.eu/q/https://github.com/copper-project/copper-rs/wiki/Copper-Release-Log

#programming #robotics #rustlang

Copper Release Log

Purpose-built, Rust-native software engine for robotics - copper-project/copper-rs

GitHub
Show threadRobotics papersDec 3, 2024

"Unlike vision and language, data for learning is not available passively[...]. This makes applying the same recipes we did in vision and language challenging"

#real2sim is a strong emergent tendency in robotics this year.

See previously shared articles:
RoboGSim -> https://arxiv.org/abs/2411.11839
RL-GSBridge -> https://arxiv.org/abs/2409.20291
GARField -> https://arxiv.org/abs/2410.05038

RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator

Efficient acquisition of real-world embodied data has been increasingly critical. However, large-scale demonstrations captured by remote operation tend to take extremely high costs and fail to scale up the data size in an efficient manner. Sampling the episodes under a simulated environment is a promising way for large-scale collection while existing simulators fail to high-fidelity modeling on texture and physics. To address these limitations, we introduce the RoboGSim, a real2sim2real robotic simulator, powered by 3D Gaussian Splatting and the physics engine. RoboGSim mainly includes four parts: Gaussian Reconstructor, Digital Twins Builder, Scene Composer, and Interactive Engine. It can synthesize the simulated data with novel views, objects, trajectories, and scenes. RoboGSim also provides an online, reproducible, and safe evaluation for different manipulation policies. The real2sim and sim2real transfer experiments show a high consistency in the texture and physics. Moreover, the effectiveness of synthetic data is validated under the real-world manipulated tasks. We hope RoboGSim serves as a closed-loop simulator for fair comparison on policy learning. More information can be found on our project page https://robogsim.github.io/ .

arXiv.org
Robotics papersDec 3, 2024

Robot Learning with Super-Linear Scaling

Authors: Marcel Torne, Arhan Jain, Jiayi Yuan, Vidaaranya Macha, Lars Ankile, Anthony Simeonov, Pulkit Agrawal, Abhishek Gupta

pre-print -> https://arxiv.org/abs/2412.01770v1
website -> https://casher-robot-learning.github.io/CASHER/

#robotics #rl #reinforcement_learning #data_generation #real2sim2real

Robot Learning with Super-Linear Scaling

Scaling robot learning requires data collection pipelines that scale favorably with human effort. In this work, we propose Crowdsourcing and Amortizing Human Effort for Real-to-Sim-to-Real(CASHER), a pipeline for scaling up data collection and learning in simulation where the performance scales superlinearly with human effort. The key idea is to crowdsource digital twins of real-world scenes using 3D reconstruction and collect large-scale data in simulation, rather than the real-world. Data collection in simulation is initially driven by RL, bootstrapped with human demonstrations. As the training of a generalist policy progresses across environments, its generalization capabilities can be used to replace human effort with model generated demonstrations. This results in a pipeline where behavioral data is collected in simulation with continually reducing human effort. We show that CASHER demonstrates zero-shot and few-shot scaling laws on three real-world tasks across diverse scenarios. We show that CASHER enables fine-tuning of pre-trained policies to a target scenario using a video scan without any additional human effort. See our project website: https://casher-robot-learning.github.io/CASHER/

arXiv.org
Show threadRobotics papersNov 28, 2024

New synthetic dataset just dropped for the folks in articulated objects manipulation !

▶️ 918 object instances
▶️ 240k photo-realistic rendering images
▶️ 8 billion scene-level actionable interaction poses

⚠️ Data not released yet

Robotics papersNov 28, 2024

GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation

Authors: Wenbo Cui, Chengyang Zhao, Songlin Wei, Jiazhao Zhang, Haoran Geng, Yaran Chen, He Wang

pre-print -> https://arxiv.org/abs/2411.18276

#robotics #articulated_objects #manipulation #dataset #synthetic_data #data_generation

GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation

Effectively manipulating articulated objects in household scenarios is a crucial step toward achieving general embodied artificial intelligence. Mainstream research in 3D vision has primarily focused on manipulation through depth perception and pose detection. However, in real-world environments, these methods often face challenges due to imperfect depth perception, such as with transparent lids and reflective handles. Moreover, they generally lack the diversity in part-based interactions required for flexible and adaptable manipulation. To address these challenges, we introduced a large-scale part-centric dataset for articulated object manipulation that features both photo-realistic material randomization and detailed annotations of part-oriented, scene-level actionable interaction poses. We evaluated the effectiveness of our dataset by integrating it with several state-of-the-art methods for depth estimation and interaction pose prediction. Additionally, we proposed a novel modular framework that delivers superior and robust performance for generalizable articulated object manipulation. Our extensive experiments demonstrate that our dataset significantly improves the performance of depth perception and actionable interaction pose prediction in both simulation and real-world scenarios. More information and demos can be found at: https://pku-epic.github.io/GAPartManip/.

arXiv.org