Sökning: onr:"swepub:oai:DiVA.org:liu-197928" >
Evaluation of Diffe...
Evaluation of Differentially Constrained Motion Models for Graph-Based Trajectory Prediction
-
- Westny, Theodor (författare)
- Linköping University,Linköpings universitet,Fordonssystem,Tekniska fakulteten
-
- Oskarsson, Joel (författare)
- Linköping University,Linköpings universitet,Statistik och maskininlärning,Tekniska fakulteten
-
- Olofsson, Björn (författare)
- Linköping University,Lund University,Lunds universitet,Linköpings universitet,Fordonssystem,Tekniska fakulteten,Lund Univ, Sweden,Institutionen för reglerteknik,Institutioner vid LTH,Lunds Tekniska Högskola,LTH profilområde: AI och digitalisering,LTH profilområden,LTH profilområde: Teknik för hälsa,LU profilområde: Naturlig och artificiell kognition,Lunds universitets profilområden,Department of Automatic Control,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH,LTH Profile Area: Engineering Health,Faculty of Engineering, LTH,LU Profile Area: Natural and Artificial Cognition,Lund University Profile areas
-
visa fler...
-
- Frisk, Erik (författare)
- Linköping University,Linköpings universitet,Fordonssystem,Tekniska fakulteten
-
visa färre...
-
(creator_code:org_t)
- IEEE, 2023
- 2023
- Engelska.
-
Ingår i: 2023 IEEE INTELLIGENT VEHICLES SYMPOSIUM, IV. - : IEEE. - 9798350346916 - 9798350346923
- Relaterad länk:
-
https://arxiv.org/ab... (free)
-
visa fler...
-
http://dx.doi.org/10...
-
https://urn.kb.se/re...
-
https://doi.org/10.1...
-
https://lup.lub.lu.s...
-
visa färre...
Abstract
Ämnesord
Stäng
- Given their flexibility and encouraging performance, deep-learning models are becoming standard for motion prediction in autonomous driving. However, with great flexibility comes a lack of interpretability and possible violations of physical constraints. Accompanying these data-driven methods with differentially-constrained motion models to provide physically feasible trajectories is a promising future direction. The foundation for this work is a previously introduced graph-neural-network-based model, MTP-GO. The neural network learns to compute the inputs to an underlying motion model to provide physically feasible trajectories. This research investigates the performance of various motion models in combination with numerical solvers for the prediction task. The study shows that simpler models, such as low-order integrator models, are preferred over more complex, e.g., kinematic models, to achieve accurate predictions. Further, the numerical solver can have a substantial impact on performance, advising against commonly used first-order methods like Euler forward. Instead, a second-order method like Heuns can greatly improve predictions.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas