Trajectory planning for meal assist robot considering spilling avoidance

Kuriyama, Yoshifumi; Yano, Ken'ichi; Hamaguchi, Masafumi

doi:10.1109/cca.2008.4629665

Cited by 14 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The system is mainly made from aluminum alloy together with other compositions. There are also some other meal feeding assistive devices for elderly, however such assistive devices have no effect on conducing people's involvement in that process [40,41].…”

Section: Mechanism Designmentioning

confidence: 99%

State-of-the-Art Assistive Powered Upper Limb Exoskeletons for Elderly

2020

View full text Add to dashboard Cite

The number of older people is growing rapidly around the world. Ageing process results in reduced or restricted mobility which is essential to perform activities of daily living. Currently, there are numerous powered assistive exoskeletons commercially available as well as are being developed to support and rehabilitate lower limbs. Significant attention is also been given to develop upper limb rehabilitation devices, however the question of what kind of assistive devices can be used by elderly group of people for their upper limbs and what technical characteristics they should incorporate is not properly researched. This paper presents the state of the art of currently available assistive exoskeletons which can be exploited to support the motions of upper limbs of elderly to perform activities of daily living. Mechanism type, degrees of freedom, type actuators and materials selected for the fabrication of these porotypes are presented in detail. Also, the type of control systems utilized for these upper limb exoskeletons are discussed in detail with the insight on the feedback signal methods. A detailed discussion on the challenges in the fields of mechanism development, actuation and control for these upper limb powered exoskeletons is presented with the opportunities for future technological developments.

show abstract

Section: Mechanism Designmentioning

confidence: 99%

State-of-the-Art Assistive Powered Upper Limb Exoskeletons for Elderly

2020

View full text Add to dashboard Cite

show abstract

“…Our solution is to use stochastic optimization to automatically search for successful pouring trajectories similar to [5] in 2D workspaces. We introduce several kinds of variations so that the learned neural network can be generalized to different problems.…”

Section: A Training Data Generationmentioning

confidence: 99%

“…On the other hand, methods using reinforcement learning [3], [4] can take physics constraints into consideration but require a problem specific training dataset for each manipulation task. Other techniques use trajectory optimization, which takes into account a full-featured liquid dynamics model [5], [6], but these techniques have a very high computational overhead. This problem can be alleviated using reduced 1 From the training dataset found by stochastic optimization (a), we train a neural network that predicts liquid-related parameters: liquid outflow curve and the mean trajectory prior (b).…”

Section: Introductionmentioning

confidence: 99%

Feedback motion planning for liquid pouring using supervised learning

Pan

Manocha

2017

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

View full text Add to dashboard Cite

We present a novel motion planning algorithm for pouring a liquid body from a source to a target container. Our approach uses a receding-horizon optimization strategy that takes into account liquid dynamics and various other constraints. In order to handle liquid dynamics without costly fluid simulations, we use a neural network to infer a set of key liquid-related parameters from the observation of current liquid configuration. To train the neural network, we generate a dataset of successful pouring examples using stochastic optimization in a problem-specific search space. These parameters are then used in the objective function for trajectory optimization. Our feedback motion planner achieves real-time performance, and we observe a high success rate in our simulated 2D and 3D liquid pouring benchmarks.

show abstract

“…The development of a fluid flow model for a bottle with a complex shape can be aided by computational fluid dynamics (CFD). In this regard, we have previously used a CFD simulator to optimize the trajectory planning of a spoon that contains a liquid [2] and to optimize the flow of molten metal in casting [3], [4].…”

Section: Introductionmentioning

confidence: 99%

Motion curve optimization of intermittent conveyance bottling machine for reducing liquid vibration

Kanazawa

Yasuya

Kato

et al. 2012

2012 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)

Self Cite

View full text Add to dashboard Cite

Recently, the need to accelerate the operating cycle of bottling machines while maintaining low operation cost has arisen. However, conveying bottles at high speed without spilling the liquids inside requires advanced techniques for vibration suppression control. In this paper, we optimize the motion curve for an intermittent conveyance bottling machine by using computational fluid dynamics (CFD) simulation to decrease residual vibration at the surface of the liquid. Additionally, we propose a method for assigning magnitude relations to variables and defining the curve by using variable transformations.

show abstract

Trajectory planning for meal assist robot considering spilling avoidance

Cited by 14 publications

References 8 publications

State-of-the-Art Assistive Powered Upper Limb Exoskeletons for Elderly

State-of-the-Art Assistive Powered Upper Limb Exoskeletons for Elderly

Feedback motion planning for liquid pouring using supervised learning

Motion curve optimization of intermittent conveyance bottling machine for reducing liquid vibration

Contact Info

Product

Resources

About