Equipping robot control programs with first-order probabilistic reasoning capabilities

Abstract

Abstract-An autonomous robot system that is to act in a real-world environment is faced with the problem of having to deal with a high degree of both complexity as well as uncertainty. Therefore, robots should be equipped with a knowledge representation system that is able to soundly handle both aspects. In this paper, we thus introduce an architecture that provides a coupling between plan-based robot controllers and a probabilistic knowledge representation system based on recent developments in statistical relational learning, which possesses the required level of expressiveness and generality. We outline possible applications of the corresponding models in the context of robot control, discussing suitable representation formalisms, inference and learning methods as well as transparent extensions of a robot planning language that allow robot control programs to soundly integrate the results of probabilistic inference into their plan generation process.

Learning task constraints for robot grasping using graphical models

“…Concluding, we observe that most of the named references are either emphasizing higher-level planning systems [6], [7], or different domains with less complexity [2], [10], [11]. Even [4], though placed in the same domain of grasp affordance learning, is applied on fairly simple manipulation actions with discretely valued properties.…”

“…The main challenges originate from the representational differences in the two research fields. [6] addresses this problem through statistical relational models for a high-level symbolic reasoner, which is integrated into a robot controller. [7] proposes a coherent control, trajectory optimization, and Recently, imitation learning [8] and the concept of internal models [9] have received considerable attention in the field of robotics.…”

Infinite Latent Conditional Random Fields for Modeling Environments through Humans

“…To our best knowledge, there is little work about arranging/placing objects in robotics (e.g., [7,30,11,16,15]), and none of these works consider reasonable arrangements for human usage. In recent work, Jiang et al [14], Jiang and Saxena [13] considered hallucinating humans for object placements and later applied similar idea to the task of scene labeling [17].…”

Hallucinating Humans for Learning Robotic Placement of Objects

“…There are some recent works using symbolic reasoning engines to plan complex manipulations for human activities, such as setting a dinner table (e.g. [18][19][20]). However, these works focus on generating parameterized actions and task-level plans instead of finding specific placements, and hence are complementary to ours.…”