| 1. |
- Almeida, Tiago, 1996-, et al.
(författare)
-
THÖR-Magni : Comparative Analysis of Deep Learning Models for Role-Conditioned Human Motion Prediction
- 2023
-
Ingår i: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). - : IEEE. - 9798350307450 - 9798350307443 ; , s. 2192-2201
-
Konferensbidrag (refereegranskat)abstract
- Autonomous systems, that need to operate in human environments and interact with the users, rely on understanding and anticipating human activity and motion. Among the many factors which influence human motion, semantic attributes, such as the roles and ongoing activities of the detected people, provide a powerful cue on their future motion, actions, and intentions. In this work we adapt several popular deep learning models for trajectory prediction with labels corresponding to the roles of the people. To this end we use the novel THOR-Magni dataset, which captures human activity in industrial settings and includes the relevant semantic labels for people who navigate complex environments, interact with objects and robots, work alone and in groups. In qualitative and quantitative experiments we show that the role-conditioned LSTM, Transformer, GAN and VAE methods can effectively incorporate the semantic categories, better capture the underlying input distribution and therefore produce more accurate motion predictions in terms of Top-K ADE/FDE and log-likelihood metrics.
|
|
| 2. |
- Schreiter, Tim, 1997-, et al.
(författare)
-
The Magni Human Motion Dataset : Accurate, Complex, Multi-Modal, Natural, Semantically-Rich and Contextualized
- 2022
-
Konferensbidrag (refereegranskat)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.
|
|
| 3. |
- Almeida, Tiago Rodrigues de, 1996-, et al.
(författare)
-
Trajectory Prediction for Heterogeneous Agents : A Performance Analysis on Small and Imbalanced Datasets
- 2024
-
Ingår i: IEEE Robotics and Automation Letters. - : IEEE. - 2377-3766. ; 9:7, s. 6576-6583
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
| 4. |
- Zhu, Yufei, 1994-, et al.
(författare)
-
CLiFF-LHMP : Using Spatial Dynamics Patterns for Long-Term Human Motion Prediction
- 2023
-
Ingår i: 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 01-05 October 2023, Detroit, MI, USA. - : IEEE. - 9781665491914 - 9781665491907 ; , s. 3795-3802
-
Konferensbidrag (refereegranskat)abstract
- Human motion prediction is important for mobile service robots and intelligent vehicles to operate safely and smoothly around people. The more accurate predictions are, particularly over extended periods of time, the better a system can, e.g., assess collision risks and plan ahead. In this paper, we propose to exploit maps of dynamics (MoDs, a class of general representations of place-dependent spatial motion patterns, learned from prior observations) for long-term human motion prediction (LHMP). We present a new MoD-informed human motion prediction approach, named CLiFF-LHMP, which is data efficient, explainable, and insensitive to errors from an upstream tracking system. Our approach uses CLiFF -map, a specific MoD trained with human motion data recorded in the same environment. We bias a constant velocity prediction with samples from the CLiFF-map to generate multi-modal trajectory predictions. In two public datasets we show that this algorithm outperforms the state of the art for predictions over very extended periods of time, achieving 45 % more accurate prediction performance at 50s compared to the baseline.
|
|
