Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots

Johnson, Jacob J.; Li, Linjun; Liu, Fei; Qureshi, Ahmed H.; Yip, Michael C.

doi:10.1109/iros45743.2020.9341283

Cited by 29 publications

(15 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Kendala non-holonomik diatur oleh persamaan dinamis yang bergantung pada turunan waktu dari ruang konfigurasi sistem [12,22,23]. Kendala tersebut muncul di banyak aplikasi, mulai dari navigasi mobile robot hingga needle steering dalam operasi robot [24].…”

Section: Pendahuluanunclassified

“…Perhitungan kendala (konstrain) TT diselesaikan dengan metode Jellet Invarian (JI). Kendala adalah kondisi yang membatasi pergerakan sistem mekanis yang mengurangi baik derajat kebebasan maupun jangkauan setiap derajat kebebasan [23]. Skema dinamika TT dapat dilihat pada Gambar 1 di bawah ini, Gambar 2 menunjukkan dinamika TT dengan sudut elevasi (𝜃) bervariasi dari 0.1 rad samapai 0.9 rad saat pertama kali dimainkan (𝑡 = 0).…”

Section: Hasil Dan Pembahasanunclassified

See 1 more Smart Citation

Pemodelan Dinamika Tippe Top (Tt) Dengan Kendala Non-Holonomik Berbasis Komputasi Fisika Pada Bidang Datar (R^2×so(3))

Ariska

Akhsan

Muslim

2021

JoP

View full text Add to dashboard Cite

Pemodelan sistem dinamik dalam real time sangat penting dalam kemajuan teknologi otomatis yang berkembang pesat saat ini, seperti metode perencanaan sistem robotic. Artikel ini menjelaskan sistem dinamik benda tegar dengan kendala non-holonomic pada ruang konfigurasi . Metode yang digunakan adalah Motion Planning Network dan simulasi numeric dengan komputasi fisika yang dapat digunakan untuk sistem benda non-holonomik yang bergerak secara real-time dengan Pendekatan Jellet Invarian (JI). Pendekatan JI dapat menghasilkan persamaan sistem gerak dan mengevaluasi simulasi model benda dengan kendala non holonomik dan juga menampilkan hasil eksperimen dinamika benda tegar dalam ruang konfigurasi . Sistem gerak benda dengan kendala non holonomik yang digunakan adalah Tippe top (TT). TT adalah mainan yang mirip seperti gasing yang jika diputar dapat membalik sendiri dengan batangnya. Penulis berhasil mendeskripsikan dinamika gerak TT secara real time dengan syarat awal bervariasi pada ruang konfigurasi .

show abstract

Section: Pendahuluanunclassified

Section: Hasil Dan Pembahasanunclassified

Pemodelan Dinamika Tippe Top (Tt) Dengan Kendala Non-Holonomik Berbasis Komputasi Fisika Pada Bidang Datar (R^2×so(3))

Ariska

Akhsan

Muslim

2021

JoP

View full text Add to dashboard Cite

show abstract

“…Qureshi et al formulate constraints into MPNet, and present CoMPNet, which encompasses kinematic constraints [33]. A similar work is done in [34]. Bency et al present OracleNet, a recurrent neural network (RNN)-based approach to generate fast near-optimal paths for robotic arms [35].…”

Section: Related Workmentioning

confidence: 99%

Waypoint Planning Networks

Toma

Jaafar

Hsueh

et al. 2021

Preprint

View full text Add to dashboard Cite

With the recent advances in machine learning, path planning algorithms are also evolving; however, the learned path planning algorithms often have difficulty competing with success rates of classic algorithms. We propose waypoint planning networks (WPN), a hybrid algorithm based on LSTMs with a local kernel-a classic algorithm such as A*, and a global kernel using a learned algorithm. WPN produces a more computationally efficient and robust solution. We compare WPN against A*, as well as related works including motion planning networks (MPNet) and value iteration networks (VIN). In this paper, the design and experiments have been conducted for 2D environments. Experimental results outline the benefits of WPN, both in efficiency and generalization. It is shown that WPN's search space is considerably less than A*, while being able to generate near optimal results. Additionally, WPN works on partial maps, unlike A* which needs the full map in advance. The code is available online 1 .

show abstract

“…Other recent work has been devoted to machine learning and variatial approaches to the problem; for example, [20], [21], [22]. Such approaches often rely on a hierarchical algorithms with global trajectory generation and local collision avoidance as in [23], [24].…”

Section: Introductionmentioning

confidence: 99%

Time-Optimal Paths for Simple Cars with Moving Obstacles in the Hamilton-Jacobi Formulation

Parkinson¹,

Ceccia²

2021

Preprint

View full text Add to dashboard Cite

We consider the problem of time-optimal path planning for simple nonholonomic vehicles. In previous similar work, the vehicle has been simplified to a point mass and the obstacles have been stationary. Our formulation accounts for a rectangular vehicle, and involves the dynamic programming principle and a time-dependent Hamilton-Jacobi-Bellman (HJB) formulation which allows for moving obstacles. To our knowledge, this is the first HJB formulation of the problem which allows for moving obstacles. We design an upwind finite difference scheme to approximate the equation and demonstrate the efficacy of our model with a few synthetic examples.

show abstract

Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots

Cited by 29 publications

References 23 publications

Pemodelan Dinamika Tippe Top (Tt) Dengan Kendala Non-Holonomik Berbasis Komputasi Fisika Pada Bidang Datar (R^2×so(3))

Pemodelan Dinamika Tippe Top (Tt) Dengan Kendala Non-Holonomik Berbasis Komputasi Fisika Pada Bidang Datar (R^2×so(3))

Waypoint Planning Networks

Time-Optimal Paths for Simple Cars with Moving Obstacles in the Hamilton-Jacobi Formulation

Contact Info

Product

Resources

About