A multi-objective optimization design of industrial robot arms

Kouritem, Sallam A.; Abouheaf, Mohammed I.; Nahas, Nabil; Hassan, Mohamed

doi:10.1016/j.aej.2022.06.052

Cited by 33 publications

(16 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, robot designs are made by human experts who rely on heuristics to optimize the structure. A number of approaches have been developed to algorithmically assist designers in making better physical structures [4], [5], improving reachability [6], [7], [8], and observability of the workspace [9], [10], [11]. However, heuristic approaches don't offer any insight on the design's performance on actual tasks.…”

Section: A Morphology Optimizationmentioning

confidence: 99%

“…Finally, we investigate the direction of task-based regularization, through the exposure of the robot to a wider set of manipulation tasks. There exists a large number of regularization approaches applied during the optimization to improve the practicality of the design such as energy, or material penalties [4], [5]. However, we intend to avoid an explicit regularization that can directly impact the final morphology.…”

Section: Multitask-based Regularizationmentioning

confidence: 99%

“…For Correspondence to: maks@gatech.edu * The research was conducted during Residency at Everyday Robots. 1 Everyday Robots, 2 Georgia Institute of Technology, 3 Robotics at Google 4 Stanford University, 5 Work done while at Everyday Robots instance, it will be extremely expensive to formulate a typical two-loop design optimization process, which searches robot morphologies in the outer loop and trains a policy for each given design in the inner loop. As such, traditional design optimization techniques focus on enhancing certain attributes in isolation or exploring based on hand-designed heuristics.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Learning to Navigate Sidewalks in Outdoor Environments

Sorokin

Tan

Liu

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

As robots become more prevalent, optimizing their design for better performance and efficiency is becoming increasingly important. However, current robot design practices overlook the impact of perception and design choices on a robot's learning capabilities. To address this gap, we propose a comprehensive methodology that accounts for the interplay between the robot's perception, hardware characteristics, and task requirements. Our approach optimizes the robot's morphology holistically, leading to improved learning and task execution proficiency. To achieve this, we introduce a Morphology-AGnostIc Controller (MAGIC), which helps with the rapid assessment of different robot designs. The MAGIC policy is efficiently trained through a novel PRIvileged Single-stage learning via latent alignMent (PRISM) framework, which also encourages behaviors that are typical of robot onboard observation. Our simulation-based results demonstrate that morphologies optimized holistically improve the robot performance by 15-20% on various manipulation tasks, and require 25x less data to match human-expert made morphology performance. In summary, our work contributes to the growing trend of learning-based approaches in robotics and emphasizes the potential in designing robots that facilitate better learning. The project's website can be found at learning-robot.github.io

show abstract

Section: A Morphology Optimizationmentioning

confidence: 99%

Section: Multitask-based Regularizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to Navigate Sidewalks in Outdoor Environments

Sorokin

Tan

Liu

et al. 2022

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…In [4], the weight reduction of the frame under strength conditions was carried out by using finite element analysis software, so that the overall shape and size were reduced under the condition of reducing the maximum stress, and the lightweight design of the structure was realized. In [5], a target design mechanism was used to determine the vulnerable position of the robot arm structure, and vibration analysis was conducted to enhance dynamic characteristics. Finally, it proposed the use of lightweight materials to achieve both static and dynamic performance improvement and lightweight.…”

Section: Introductionmentioning

confidence: 99%

Topology optimization of the wheel frame of the tracked robot with multiple working conditions and multiple objectives

Wang,

Huang,

et al. 2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Based on ensuring the static stiffness and dynamic vibration frequency of the caterpillar robot wheel frame under various working conditions, the lightweight design of the caterpillar robot wheel frame is realized. The compromise programming approach is used to establish the multi-objective optimization function and three typical target conditions are simulated and analyzed. An analytic hierarchy process is used to determine the weight coefficient of each target working condition, and the topology optimization of the wheel frame of the tracked robot is carried out comprehensively, considering multi-working conditions and multi-target. The secondary design of the optimized rear wheel frame was carried out, as a result of which, the mass was reduced by 8.4% after optimization, and the first-order frequency was increased by 20 Hz after optimization. The optimized rear wheel frame strength and stiffness met the requirements.

show abstract

“…Bani-Hani et al (Bani-Hani et al 2023) proposed a Genetic Algorithm optimization technique to harvest power of Impact Force that be utilized as a sensing device, Analytical and Finite Element Investigation Naqvi et al (Naqvi et al 2022;Shaukat et al 2023) presented a complete review of some vibration sources. Some parameters are optimized in this paper using the iterative optimization technique (Kouritem and Elshabasy 2021;Elshabasy and Kouritem 2020;Kouritem et al 2022c).…”

Section: Introductionmentioning

confidence: 99%

Effect of major factors on broadband natural frequency energy harvesting for rectangular and L- shaped cantilever harvesters

2023

Self Cite

View full text Add to dashboard Cite

A small amount of natural frequency deviation extremely decreases the output power. So, a multi-mass single harvester (bending harvester) was utilized to enlarge the bandwidth of the natural frequency. We constructed three models to study the effect of increasing the concentrated masses on increasing the bandwidth natural frequency. We used Finite Element Metho (FEM (COMSOL to model and simulate the three models. Moreover, we constructed an L-shaped harvester with concentrated masses to compare the rectangular harvester with concentrated masses. The results prove that increasing the number of concentrated masses increases the output power and broadband natural frequency. Moreover, the results indicate that the harvester cantilever with concentrated masses gives more output power and broadband than the L- shaped harvester for the same volume. Also, our research studied the harvester parameter effects on the output power. This study found that the increase in beam length and mass height increases the output power while the increase in piezoelectric thickness and damping ratio decreases the output power and bandwidth frequency. We validated our proposed model through a comparison with others’ preceding experimental results and it showed a good agreement. The harvester with a high width/length ratio gives a larger wideband natural frequency.

show abstract

A multi-objective optimization design of industrial robot arms

Cited by 33 publications

References 37 publications

Learning to Navigate Sidewalks in Outdoor Environments

Learning to Navigate Sidewalks in Outdoor Environments

Topology optimization of the wheel frame of the tracked robot with multiple working conditions and multiple objectives

Effect of major factors on broadband natural frequency energy harvesting for rectangular and L- shaped cantilever harvesters

Contact Info

Product

Resources

About