Long-term path prediction in urban scenarios using circular distributions

Abstract

Human ability to foresee the near future plays a key role in everyone's life to prevent potentially dangerous situations. To be able to make predictions is crucial when people have to interact with the surrounding environment. Modeling such capability can lead to the design of automated warning systems and provide moving robots with an intelligent way of interaction with changing situation.

Human motion trajectory prediction: a survey

“… 1.1. Single-model methods define a single dynamical motion model (e.g., Aoude et al, 2010; Coscia et al, 2018; Elnagar, 2001; Luber et al, 2010; Pellegrini et al, 2009; Petrich et al, 2013; Yamaguchi et al, 2011; Zernetsch et al, 2016). 1.2.…”

“…map-aware methods , which account for environment geometry and topology (e.g., Chen et al, 2017; Chung and Huang, 2010, 2012; Gong et al, 2011; Henry et al, 2010; Ikeda et al, 2012; Kooij et al, 2019; Liao et al, 2003; Pfeiffer et al, 2016; Pool et al, 2017; Rösmann et al, 2017; Rudenko et al, 2017, 2018b; Vasquez, 2016; Yen et al, 2008; Ziebart et al, 2009); 3.4. semantics-aware methods , which additionally account for environment semantics or affordances such as no-go zones, crosswalks, sidewalks, or traffic lights (e.g., Ballan et al, 2016; Coscia et al, 2018; Karasev et al, 2016; Kitani et al, 2012; Kuhnt et al, 2016; Lee et al, 2017; Ma et al, 2017; Rehder et al, 2018; Zheng et al, 2016). …”

“…3.4. semantics-aware methods , which additionally account for environment semantics or affordances such as no-go zones, crosswalks, sidewalks, or traffic lights (e.g., Ballan et al, 2016; Coscia et al, 2018; Karasev et al, 2016; Kitani et al, 2012; Kuhnt et al, 2016; Lee et al, 2017; Ma et al, 2017; Rehder et al, 2018; Zheng et al, 2016).…”

“…When agents move freely, e.g., do not comply with road constraints, we need different ways to represent free space and account for map information. To this end, several authors proposed grid-based (Coscia et al, 2018; Luber et al, 2011; Rehder and Klöden, 2015) and more general graph-based space discretizations (Aoude et al, 2010; Koschi et al, 2018). Luber et al (2011) used 2D laser data to track people from a mobile robot and learn a so-called spatial affordance map, a grid-based spatial Poisson process from which a walkable area map of the environment can be derived.…”

Social and Scene-Aware Trajectory Prediction in Crowded Spaces

“…[2] proposes a Bayesian framework based on previously observed motions to infer unobserved paths and for transferring learned motions to unobserved scenes. Similarly, in [6] circular distributions model dynamics and semantics for long-term trajectory predictions. [19] uses past observations along with bird's eye view images based on a two-levels attention mechanism.…”