| 1. |
- Kucner, Tomasz Piotr, PhD, 1988-, et al.
(författare)
-
Probabilistic Mapping of Spatial Motion Patterns for Mobile Robots
- 2020
-
Bok (övrigt vetenskapligt/konstnärligt)abstract
- This book describes how robots can make sense of motion in their surroundings and use the patterns they observe to blend in better in dynamic environments shared with humans.The world around us is constantly changing. Nonetheless, we can find our way and aren’t overwhelmed by all the buzz, since motion often follows discernible patterns. Just like humans, robots need to understand the patterns behind the dynamics in their surroundings to be able to efficiently operate e.g. in a busy airport. Yet robotic mapping has traditionally been based on the static world assumption, which disregards motion altogether. In this book, the authors describe how robots can instead explicitly learn patterns of dynamic change from observations, store those patterns in Maps of Dynamics (MoDs), and use MoDs to plan less intrusive, safer and more efficient paths. The authors discuss the pros and cons of recently introduced MoDs and approaches to MoD-informed motion planning, and provide an outlook on future work in this emerging, fascinating field.
|
|
| 2. |
- Palmieri, Luigi, et al.
(författare)
-
Guest Editorial : Introduction to the Special Issue on Long-Term Human Motion Prediction
- 2021
-
Ingår i: IEEE Robotics and Automation Letters. - : IEEE Press. - 2377-3766. ; 6:3, s. 5613-5617
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)abstract
- The articles in this special section focus on long term human motion prediction. This represents a key ability for advanced autonomous systems, especially if they operate in densely crowded and highly dynamic environments. In those settings understanding and anticipating human movements is fundamental for robust long-term operation of robotic systems and safe human-robot collaboration. Foreseeing how a scene with multiple agents evolves over time and incorporating predictions in a proactive manner allows for novel ways of planning and control, active perception, or humanrobot interaction. Recent planning and control approaches use predictive techniques to better cope with the dynamics of the environment, thus allowing the generation of smoother and more legible robot motion. Predictions can be provided as input to the planning or optimization algorithm (e.g. as a cost term or heuristic function), or as additional dimension to consider in the problem formulation (leading to an increased computational complexity). Recent perception techniques deeply interconnect prediction modules with detection, segmentation and tracking, to generally increase the accuracy of different inference tasks, i.e. filtering, predicting. As also indicated by some of the scientific works accepted in this special issue, novel deep learning architectures allow better interleaving of the aforementioned units.
|
|
