Sökning: WFRF:(Almeida Tiago 1996 ) >
Trajectory Predicti...
Trajectory Prediction for Heterogeneous Agents : A Performance Analysis on Small and Imbalanced Datasets
-
- Almeida, Tiago Rodrigues de, 1996- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems
-
- Zhu, Yufei, 1994- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems
-
- Rudenko, Andrey (författare)
- Robert Bosch GmbH, Corporate Research, Stuttgart, Germany
-
visa fler...
-
- Kucner, Tomasz P. (författare)
- School of Electrical Engineering, Aalto University, Espoo, Finland; Finnish Center for Artificial Intelligence, Aalto, Finland
-
- Stork, Johannes A, 1986- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems
-
- Magnusson, Martin, Docent, 1977- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Centre for Applied Autonomous Sensor Systems
-
- Lilienthal, Achim J, 1970- (författare)
- Örebro universitet,Institutionen för naturvetenskap och teknik,Technical University of Munich, Munich, Germany
-
visa färre...
-
(creator_code:org_t)
- IEEE, 2024
- 2024
- Engelska.
-
Ingår i: IEEE Robotics and Automation Letters. - : IEEE. - 2377-3766. ; 9:7, s. 6576-6583
- Relaterad länk:
-
https://urn.kb.se/re...
-
visa fler...
-
https://doi.org/10.1...
-
visa färre...
Abstract
Ämnesord
Stäng
- Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly depends on their tasks, roles, or observable labels. Class-conditioned motion prediction is thus an appealing way to reduce forecast uncertainty and get more accurate predictions for heterogeneous agents. However, this is hardly explored in the prior art, especially for mobile robots and in limited data applications. In this paper, we analyse different class-conditioned trajectory prediction methods on two datasets. We propose a set of conditional pattern-based and efficient deep learning-based baselines, and evaluate their performance on robotics and outdoors datasets (TH & Ouml;R-MAGNI and Stanford Drone Dataset). Our experiments show that all methods improve accuracy in most of the settings when considering class labels. More importantly, we observe that there are significant differences when learning from imbalanced datasets, or in new environments where sufficient data is not available. In particular, we find that deep learning methods perform better on balanced datasets, but in applications with limited data, e.g., cold start of a robot in a new environment, or imbalanced classes, pattern-based methods may be preferable.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datorseende och robotik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Vision and Robotics (hsv//eng)
Nyckelord
- Datasets for human motion
- deep learning methods
- human and humanoid motion analysis and synthesis
- human detection and tracking
Publikations- och innehållstyp
- ref (ämneskategori)
- art (ämneskategori)
Hitta via bibliotek
Till lärosätets databas