Context-Based Path Prediction for Targets with Switching Dynamics

Abstract

Anticipating future situations from streaming sensor data is a key perception challenge for mobile robotics and automated vehicles. We address the problem of predicting the path of objects with multiple dynamic modes. The dynamics of such targets can be described by a Switching Linear Dynamical System (SLDS). However, predictions from this probabilistic model cannot anticipate when a change in dynamic mode will occur. We propose to extract various types of cues with computer vision to provide context on the target's behavior, and incorporate these in a Dynamic Bayesian Network (DBN). The DBN extends the SLDS by conditioning the mode transition probabilities on additional context states. We describe efficient online inference in this DBN for probabilistic path prediction, accounting for uncertainty in both measurements and target behavior. Our approach is illustrated on two scenarios in the Intelligent Vehicles domain concerning pedestrians and cyclists, so-called Vulnerable Road Users (VRUs). Here, context cues include the static environment of the VRU, its dynamic environment, and its observed actions. Experiments using stereo vision data from a moving vehicle demonstrate that the proposed approach results in more accurate path prediction than SLDS at the relevant short time horizon (1 s). It slightly outperforms a computationally more demanding state-of-the-art method.

What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

“…Baxter et al [8] extend a Kalman Filter with an instantaneous prior belief about where people will move, based on where they are currently looking at. Kooij et al [9] describe the motion of vulnerable road users with a Dynamic Bayesian Network. Ess et al [10] and Leigh et al [11] use a Constant Velocity Model in combination with a Kalman Filter in their tracking approaches.…”

An RNN-Based IMM Filter Surrogate

“…The engineering task of finding the best model set up for IMM filters and their extensions can lead to an improved behavior (see for example Keller et al [18]) in specific maneuver situations, but is also very tedious to find a good setting. It should also be mentioned that recent work like the approaches of Kooij et al [20] show options how to further improve the prediction performance by including scene context and using more cues than pedestrian point kinematics (e.g. head orientation, gaze, body tilt, articulated body information).…”

Intention Recognition of Pedestrians and Cyclists by 2D Pose Estimation

“…Using a stereo rig, in [8], [25] it is detected whether the left arm of a cyclist observed from the back is up or down, which is used as a context cue within a path prediction module. However, an isolated accuracy analysis of such up/down arm classification is not performed.…”