Bandit-Based Model Selection for Deformable Object Manipulation

McConachie, Dale; Berenson, Dmitry

doi:10.1007/978-3-030-43089-4_45

Cited by 13 publications

(10 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach was recently extended by (McConachie and Berenson, 2016) by choosing among a set of models for this Jacobian using a multi-arm bandit formulation. Under this formulation, the "arms" were defined as models based on their diminishing rigidity and an adaptive Jacobian (as proposed by Navarro-Alarcón et al; see Section 6.3.2) with various sets of parameter.…”

Section: Multi-point Control Fanson and Patriciumentioning

confidence: 99%

Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey

Sánchez

Ramón

Bouzgarrou

et al. 2018

The International Journal of Robotics Research

389

228

View full text Add to dashboard Cite

We present a survey of recent work on robot manipulation and sensing of deformable objects, a field with relevant applications in diverse industries such as medical (e.g. surgery assistance), food handling, manufacturing, and domestic chores (e.g. folding clothes). We classify the reviewed approaches into four categories based on the type of object they manipulate. Furthermore, within this object classification we divide the approaches based on the particular task they perform on the deformable object. Finally, we conclude this survey with a discussion of the current state of the art and propose future directions within the proposed classification.

show abstract

Section: Multi-point Control Fanson and Patriciumentioning

confidence: 99%

Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey

Sánchez

Ramón

Bouzgarrou

et al. 2018

The International Journal of Robotics Research

389

228

View full text Add to dashboard Cite

show abstract

“…Yet, since it is a local model, it should be continuously updated during task execution. Model updating methods include: Broyden rules [9], receding horizon adaption [24], local gradient descent [25], QP-based optimization [26], and Multi-armed Banditbased methods [27]. Furthermore, one can design a simple controller by inverting the Jacobian model.…”

Section: Modelingmentioning

confidence: 99%

Challenges and Outlook in Robotic Manipulation of Deformable Objects

Zhu

Cherubini

Dune

et al. 2022

IEEE Robot. Automat. Mag.

Self Cite

118

View full text Add to dashboard Cite

Deformable object manipulation (DOM) is an emerging research problem in robotics. The ability to manipulate deformable objects endows robots with higher autonomy and promises new applications in the industrial, services, and healthcare sectors. However, compared to rigid object manipulation, the manipulation of deformable objects is considerably more complex, and is still an open research problem. Tackling the challenges in DOM demands breakthroughs in almost all aspects of robotics, namely hardware design, sensing, deformation modeling, planning, and control. In this article, we highlight the main challenges that arise by considering deformation and review recent advances in each sub-field. A particular focus of our paper lies in the discussions of these challenges and proposing promising directions of research.

show abstract

“…To accelerate learning, we exploit the correlation between arms, calculated as the cosine similarity between the cost weights. Our formulation fits the problem from [27] and we implement their framework for nonstationary correlated multi-arm bandits. Finally, we return to exploit mode after a fixed number of steps N R , if we returned to nominal dynamics, or if we stopped moving after leaving the initial trap state.…”

Section: B Online: Trap-aware Mpcmentioning

confidence: 99%

TAMPC: A Controller for Escaping Traps in Novel Environments

Zhong

Zhang

Fazeli

et al. 2021

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

We propose an approach to online model adaptation and control in the challenging case of hybrid and discontinuous dynamics where actions may lead to difficult-toescape "trap" states. We first learn dynamics for a given system from training data which does not contain unexpected traps (since we do not know what traps will be encountered online). These "nominal" dynamics allow us to perform tasks under ideal conditions, but when unexpected traps arise in execution, we must find a way to adapt our dynamics and control strategy and continue attempting the task. Our approach, Trap-Aware Model Predictive Control (TAMPC), is a two-level hierarchical control algorithm that reasons about traps and non-nominal dynamics to decide between goal-seeking and recovery policies. An important requirement of our method is the ability to recognize nominal dynamics even when we encounter data that is out-of-distribution w.r.t the training data. We achieve this by learning a representation for dynamics that exploits invariance in the nominal environment, thus allowing better generalization. We evaluate our method on simulated planar pushing and peg-in-hole as well as real robot peg-in-hole problems against adaptive control and reinforcement learning baselines, where traps arise due to unexpected obstacles that we only observe through contact. Our results show that our method significantly outperforms the baselines in all tested scenarios.

show abstract

Bandit-Based Model Selection for Deformable Object Manipulation

Cited by 13 publications

References 13 publications

Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey

Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey

Challenges and Outlook in Robotic Manipulation of Deformable Objects

TAMPC: A Controller for Escaping Traps in Novel Environments

Contact Info

Product

Resources

About