PACER: Preference-conditioned All-terrain Costmap Generation
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
These are Not All the Features You are Looking For: A Fundamental Bottleneck In Supervised Pretraining
BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration
Transit for All: Mapping Equitable Bike2Subway Connection using Region Representation Learning
On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning
Dual Dimensions Geometric Representation Learning Based Document Dewarping
Is Diversity All You Need for Scalable Robotic Manipulation?
토론
이 논문과 연결된 포럼 글이 아직 없습니다.