Keywords: Vision-Based Navigation, Conditional Generative Model, Cost Function
TL;DR: In this paper we presented PACER, a novel architecture and training approach to quickly produce costmaps according to arbitrary user preferences and new terrains with no fine-tuning.
Abstract: In autonomous robot navigation, terrain cost assignment is typically performed using a semantics-based paradigm in which terrain is first labeled using a pre-trained semantic classifier and costs are then assigned according to a user-defined mapping between label and cost. While this approach is rapidly adaptable to changing user preferences, only preferences over the types of terrain that are already known by the semantic classifier can be expressed. In this paper, we hypothesize that a machine-learning-based alternative to the semantics-based paradigm above will allow for rapid cost assignment adaptation to preferences expressed over *new* terrains at deployment time without the need for additional training. To investigate this hypothesis, we introduce and study *PACER*, a novel approach to costmap generation that accepts as input a single birds-eye view (BEV) image of the surrounding area along with a user-specified *preference context* and generates a corresponding BEV costmap that aligns with the preference context. Using both real and synthetic data along with a combination of proposed training tasks, we find that *PACER* is able to adapt quickly to new user preferences while also exhibiting better generalization to novel terrains compared to both semantics-based and representation-learning approaches.
Submission Number: 11
Loading