| 1. |
- Almeida, Tiago Rodrigues de, 1996-, et al.
(author)
-
Context-free Self-Conditioned GAN for Trajectory Forecasting
- 2022
-
In: 21st IEEE International Conference on Machine Learning and Applications. ICMLA 2022. - : IEEE. - 9781665462839 ; , s. 1218-1223
-
Conference paper (peer-reviewed)abstract
- In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.
|
|
| 2. |
- Schreiter, Tim, 1997-, et al.
(author)
-
The Magni Human Motion Dataset : Accurate, Complex, Multi-Modal, Natural, Semantically-Rich and Contextualized
- 2022
-
Conference paper (peer-reviewed)abstract
- Rapid development of social robots stimulates active research in human motion modeling, interpretation and prediction, proactive collision avoidance, human-robot interaction and co-habitation in shared spaces. Modern approaches to this end require high quality datasets for training and evaluation. However, the majority of available datasets suffers from either inaccurate tracking data or unnatural, scripted behavior of the tracked people. This paper attempts to fill this gap by providing high quality tracking information from motion capture, eye-gaze trackers and on-board robot sensors in a semantically-rich environment. To induce natural behavior of the recorded participants, we utilise loosely scripted task assignment, which induces the participants navigate through the dynamic laboratory environment in a natural and purposeful way. The motion dataset, presented in this paper, sets a high quality standard, as the realistic and accurate data is enhanced with semantic information, enabling development of new algorithms which rely not only on the tracking information but also on contextual cues of the moving agents, static and dynamic environment.
|
|
