Napredna pretraga

Pregled bibliografske jedinice broj: 1012034

Stochastic Optimization for Trajectory Planning with Heteroscedastic Gaussian Processes


Petrović, Luka; Peršić, Juraj; Seder, Marija; Marković, Ivan
Stochastic Optimization for Trajectory Planning with Heteroscedastic Gaussian Processes // European Conference on Mobile Robots (ECMR)
Prague, Czech Republic, 2019. str. 1-6 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Stochastic Optimization for Trajectory Planning with Heteroscedastic Gaussian Processes

Autori
Petrović, Luka ; Peršić, Juraj ; Seder, Marija ; Marković, Ivan

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
European Conference on Mobile Robots (ECMR) / - , 2019, 1-6

Skup
European Conference on Mobile Robots (ECMR)

Mjesto i datum
Prague, Czech Republic, 04.-06.09.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Motion Planning ; Trajectory Optimization ; Gaussian Processes ; Stochastic Optimization

Sažetak
Trajectory optimization methods for motion planning attempt to generate trajectories that minimize a suitable objective function. Such methods efficiently find solutions even for high degree-of-freedom robots. However, a globally optimal solution is often intractable in practice and state-of-the-art trajectory optimization methods are thus prone to local minima, especially in cluttered environments. In this paper, we propose a novel motion planning algorithm that employs stochastic optimization based on the cross-entropy method in order to tackle the local minima problem. We represent trajectories as samples from a continuous-time Gaussian process and introduce heteroscedasticity to generate powerful trajectory priors better suited for collision avoidance in motion planning problems. Our experimental evaluation shows that the proposed approach yields a more thorough exploration of the solution space and a higher success rate in complex environments than a current Gaussian process motion planning state-of-the-art trajectory optimization method, namely GPMP2, while having comparable execution time.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Temeljne tehničke znanosti



POVEZANOST RADA


Ustanove
Fakultet elektrotehnike i računarstva, Zagreb