Autonomous driving challenge: To Infer the property of a dynamic object based on its motion pattern using recurrent neural network
This addresses a critical safety challenge in autonomous driving for avoiding unnecessary maneuvers, but it is incremental as it applies an existing method (LSTM) to a new domain-specific problem.
The paper tackles the problem of distinguishing between objects that should be avoided or collided with in autonomous driving by classifying them based on motion patterns like bounciness and elasticity, using an LSTM-based recurrent neural network and demonstrating effectiveness on synthetic and limited real-world data.
In autonomous driving applications a critical challenge is to identify action to take to avoid an obstacle on collision course. For example, when a heavy object is suddenly encountered it is critical to stop the vehicle or change the lane even if it causes other traffic disruptions. However,there are situations when it is preferable to collide with the object rather than take an action that would result in a much more serious accident than collision with the object. For example, a heavy object which falls from a truck should be avoided whereas a bouncing ball or a soft target such as a foam box need not be.We present a novel method to discriminate between the motion characteristics of these types of objects based on their physical properties such as bounciness, elasticity, etc.In this preliminary work, we use recurrent neural net-work with LSTM cells to train a classifier to classify objects based on their motion trajectories. We test the algorithm on synthetic data, and, as a proof of concept, demonstrate its effectiveness on a limited set of real-world data.