Dense Object Nets (DONs) by Florence, Manuelli and Tedrake (2018) introduced dense object descriptors as a novel visual object representation for the robotics community. It is suitable for many applications including object grasping, policy learning, etc. DONs map an RGB image depicting an object into a descriptor space image, which implicitly encodes key features of an object invariant to the relative camera pose. Impressively, the self-supervised training of DONs can be applied to arbitrary objects and can be evaluated and deployed within hours. However, the training approach relies on accurate depth images and faces challenges with small, reflective objects, typical for industrial settings, when using consumer grade depth cameras. In this paper we show that given a 3D model of an object, we can generate its descriptor space image, which allows for supervised training of DONs. We rely on Laplacian Eigenmaps (LE) to embed the 3D model of an object into an optimally generated space. While our approach uses more domain knowledge, it can be efficiently applied even for smaller and reflective objects, as it does not rely on depth information. We compare the training methods on generating 6D grasps for industrial objects and show that our novel supervised training approach improves the pick-and-place performance in industry-relevant tasks.

Enabling robots to quickly learn manipulation skills is an important, yet challenging problem. Such manipulation skills should be flexible, e.g., be able adapt to the current workspace configuration. Furthermore, to accomplish complex manipulation tasks, robots should be able to sequence several skills and adapt them to changing situations. In this work, we propose a rapid robot skill-sequencing algorithm, where the skills are encoded by object-centric hidden semi-Markov models. The learned skill models can encode multimodal (temporal and spatial) trajectory distributions. This approach significantly reduces manual modeling efforts, while ensuring a high degree of flexibility and re-usability of learned skills. Given a task goal and a set of generic skills, our framework computes smooth transitions between skill instances. To compute the corresponding optimal end-effector trajectory in task space we rely on Riemannian optimal controller. We demonstrate this approach on a 7 DoF robot arm for industrial assembly tasks.

Although hippocampal grid cells are thought to be crucial for spatial navigation, their computational purpose remains disputed. Recently, they were proposed to represent spatial transitions and convey this knowledge downstream to place cells. However, a single scale of transitions is insufficient to plan long goal-directed sequences in behaviorally acceptable time. Here, a scale-space data structure is suggested to optimally accelerate retrievals from transition systems, called transition scale-space (TSS). Remaining exclusively on an algorithmic level, the scale increment is proved to be ideally [Formula: see text] for biologically plausible receptive fields. It is then argued that temporal buffering is necessary to learn the scale-space online. Next, two modes for retrieval of sequences from the TSS are presented: top down and bottom up. The two modes are evaluated in symbolic simulations (i.e., without biologically plausible spiking neurons). Additionally, a TSS is used for short-cut discovery in a simulated Morris water maze. Finally, the results are discussed in depth with respect to biological plausibility, and several testable predictions are derived. Moreover, relations to other grid cell models, multiresolution path planning, and scale-space theory are highlighted. Summarized, reward-free transition encoding is shown here, in a theoretical model, to be compatible with the observed discretization along the dorso-ventral axis of the medial entorhinal cortex. Because the theoretical model generalizes beyond navigation, the TSS is suggested to be a general-purpose cortical data structure for fast retrieval of sequences and relational knowledge. Source code for all simulations presented in this paper can be found at https://github.com/rochus/transitionscalespace .

A wide range of discrete planning problems can be solved optimally using graph search algorithms. However, optimal search quickly becomes infeasible with increased complexity of a problem. In such a case, heuristics that guide the planning process towards the goal state can increase performance considerably. Unfortunately, heuristics are often unavailable or need manual and time-consuming engineering. Building upon recent results on applying deep learning to learn generalized reactive policies, we propose to learn heuristics by imitation learning. After learning heuristics based on optimal examples, they are used to guide a classical search algorithm to solve unseen tasks. However, directly applying learned heuristics in search algorithms such as A∗ breaks optimality guarantees, since learned heuristics are not necessarily admissible. Therefore, we (i) propose a novel method that utilizes learned heuristics to guide Focal Search A∗, a variant of A∗ with guarantees on bounded suboptimality; (ii) compare the complexity and performance of jointly learning individual policies for multiple robots with an approach that learns one policy for all robots; (iii) thoroughly examine how learned policies generalize to previously unseen environments and demonstrate considerably improved performance in a simulated complex dynamic coverage problem.

Grid cells of the rodent entorhinal cortex are essential for spatial navigation. Although their function is commonly believed to be either path integration or localization, the origin or purpose of their hexagonal firing fields remains disputed. Here they are proposed to arise as an optimal encoding of transitions in sequences. First, storage requirements for transitions in general episodic sequences are examined using propositional logic and graph theory. Subsequently, transitions in complete metric spaces are considered under the assumption of an ideal sampling of an input space. It is shown that memory capacity of neurons that have to encode multiple feasible spatial transitions is maximized by a hexagonal pattern. Grid cells are proposed to encode spatial transitions in spatiotemporal sequences, with the entorhinal-hippocampal loop forming a multitransition system.