Kernel density estimation based self-learning sampling strategy for motion planning of repetitive tasks

Iversen, Thomas Fridolin; Ellekilde, Lars‐Peter

doi:10.1109/iros.2016.7759226

Cited by 17 publications

(14 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We record the arm posture data and project such data onto a low-dimensional latent space with the Gaussian Process Latent Variable Model (GP-LVM) [18]. Then, we compute the density plot of the latent space representation using the Kernel Density Estimation (KDE) [19]. This modeling method is detailed in Section IV-B.…”

Section: A Control Strategy For Personalized Assistive Dressingmentioning

confidence: 99%

See 1 more Smart Citation

Personalized robot-assisted dressing using user modeling in latent spaces

Zhang¹,

Cully²,

Demiris³

2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Robots have the potential to provide tremendous support to disabled and elderly people in their everyday tasks, such as dressing. Many recent studies on robotic dressing assistance usually view dressing as a trajectory planning problem. However, the user movements during the dressing process are rarely taken into account, which often leads to the failures of the planned trajectory and may put the user at risk. The main difficulty of taking user movements into account is caused by severe occlusions created by the robot, the user, and the clothes during the dressing process, which prevent vision sensors from accurately detecting the postures of the user in real time. In this paper, we address this problem by introducing an approach that allows the robot to automatically adapt its motion according to the force applied on the robot's gripper caused by user movements. There are two main contributions introduced in this paper: 1) the use of a hierarchical multi-task control strategy to automatically adapt the robot motion and minimize the force applied between the user and the robot caused by user movements; 2) the online update of the dressing trajectory based on the user movement limitations modeled with the Gaussian Process Latent Variable Model in a latent space, and the density information extracted from such latent space. The combination of these two contributions leads to a personalized dressing assistance that can cope with unpredicted user movements during the dressing while constantly minimizing the force that the robot may apply on the user. The experimental results demonstrate that the proposed method allows the Baxter humanoid robot to provide personalized dressing assistance for human users with simulated upper-body impairments.

show abstract

Section: A Control Strategy For Personalized Assistive Dressingmentioning

confidence: 99%

“…. , x N ) be sampled from an unknown densityf d , then estimating the shape of this function can be done with its kernel density estimator [19]…”

Section: B Upper-body Movement Modelingmentioning

confidence: 99%

Personalized robot-assisted dressing using user modeling in latent spaces

Zhang¹,

Cully²,

Demiris³

2017

2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…where |S desired | is the desired number of states. Finding the stepsize according to (7) is based on an estimate of the number of states in (6) as some states may be counted twice if they are close enough to more than one waypoint, though the algorithm is not dependent on having an exact amount of states but rather an upper bound to secure tractability.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…These planners can only guarantee a single path to be collision free, unless planning for a set of particles representing uncertainty in a starting pose [4]. Even though a number of attempts have been made to speed up path planning, including both tree structure optimization [5] and sampling methods [6], [7], it is still expensive to plan paths for many particles.…”

Section: Related Workmentioning

confidence: 99%

Adaptive motion planning in bin-picking with object uncertainties

Iversen

Ellekilde

Miró

2017

2017 17th International Conference on Control, Automation and Systems (ICCAS)

Self Cite

View full text Add to dashboard Cite

Doing motion planning for bin-picking with object uncertainties requires either a re-grasp of picked objects or an online sensor system. Using the latter is advantageous in terms of computational time, as no time is wasted doing an extra pick and place action. It does, however, put extra requirements on the motion planner, as the target position may change on-the-fly. This paper solves that problem by using a state adjusting Partial Observable Markov Decision Process, where the state space is modified between runs, to better fit earlier solved problems. The approach relies on a set of waypoints, containing information about which parts of the state space may contain feasible solutions. Waypoints are pushed around the state space by observing which states in the neighborhood lead to successfully solved problems. Two bin-picking scenarios are modeled with the proposed method. One scenario in which the system receives an object pose update while moving towards the place position. Another where the update includes the object type being grasped out of a fixed number of options, each class to be deposited in a different place. When an online POMDP solver is utilized, the state adjusting POMDP is improving performance by up to 28% on execution times compared to a not adjusted POMDP.

show abstract

“…Several techniques are available for density estimation including Multidimensional Histograms Wavelet Transformations, Discrete Cosine Transformations , and Kernel Estimators. Density‐biased sampling has found applications in clustering and outlier detection where the authors used an Epanechnikov kernel function to estimate the density function, as well as in motion planners for robotics and in magnetic resonance imaging where the authors used wavelet transformations.…”

Section: Probability Sampling Techniquesmentioning

confidence: 99%

Recent advances in scaling‐down sampling methods in machine learning

ElRafey

Wojtusiak

2017

WIREs Computational Stats

View full text Add to dashboard Cite

Data sampling methods have been investigated for decades in the context of machine learning and statistical algorithms, with significant progress made in the past few years driven by strong interest in big data and distributed computing. Most recently, progress has been made in methods that can be broadly categorized into random sampling including density-biased and nonuniform sampling methods; active learning methods, which are a type of semi-supervised learning and an area of intense research; and progressive sampling methods which can be viewed as a combination of the above two approaches. A unified view of scalingdown sampling methods is presented in this article and complemented with descriptions of relevant published literature.

show abstract

Kernel density estimation based self-learning sampling strategy for motion planning of repetitive tasks

Cited by 17 publications

References 23 publications

Personalized robot-assisted dressing using user modeling in latent spaces

Personalized robot-assisted dressing using user modeling in latent spaces

Adaptive motion planning in bin-picking with object uncertainties

Recent advances in scaling‐down sampling methods in machine learning

Contact Info

Product

Resources

About