Publications

Accurate 3D pose estimation of grasped objects is an important prerequisite for robots to perform assembly or in-hand manipulation tasks, but object occlusion by the robot's own hand greatly increases the difficulty of this perceptual task. Here, we propose that combining visual information with binary, low-resolution tactile contact measurements from across the interior surface of an articulated robotic hand can mitigate this issue. The visuo-tactile object-pose-estimation problem is formulated probabilistically in a factor graph. The pose of the object is optimized to align with the two kinds of measurements using a robust cost function to reduce the influence of outlier readings. The advantages of the proposed approach are first demonstrated in simulation: a custom 15-DOF robot hand with one binary tactile sensor per link grasps 17 YCB objects while observed by an RGB-D camera. This low-resolution in-hand tactile sensing significantly improves object-pose estimates under high occlusion and also high visual noise. We also show these benefits through grasping tests with a preliminary real version of our tactile hand, obtaining reasonable visuo-tactile estimates of object pose at approximately 12.9 Hz on average.

Wheeled mobile robots need the ability to estimate their motion and the effect of their control actions for navigation planning. In this paper, we present ST-VIO, a novel approach which tightly fuses a single-track dynamics model for wheeled ground vehicles with visual-inertial odometry (VIO). Our method calibrates and adapts the dynamics model online to improve the accuracy of forward prediction conditioned on future control inputs. The single-track dynamics model approximates wheeled vehicle motion under specific control inputs on flat ground using ordinary differential equations. We use a singularity-free and differentiable variant of the single-track model to enable seamless integration as dynamics factor into VIO and to optimize the model parameters online together with the VIO state variables. We validate our method with real-world data in both indoor and outdoor environments with different terrain types and wheels. In experiments, we demonstrate that ST-VIO can not only adapt to wheel or ground changes and improve the accuracy of prediction under new control inputs, but can even improve tracking accuracy.

Object-centric scene decompositions are important representations for downstream tasks in fields such as computer vision and robotics. The recently proposed Slot Attention module, already leveraged by several derivative works for image segmentation and object tracking in videos, is a deep learning component which performs unsupervised object-centric scene decomposition on input images. It is based on an attention architecture, in which latent slot vectors, which hold compressed information on objects, attend to localized perceptual features from the input image. In this paper, we demonstrate that design decisions on normalizing the aggregated values in the attention architecture have considerable impact on the capabilities of Slot Attention to generalize to a higher number of slots and objects as seen during training. We propose and investigate alternatives to the original normalization scheme which increase the generalization capabilities of Slot Attention to varying slot and object counts, resulting in performance gains on the task of unsupervised image segmentation. The newly proposed normalizations represent minimal and easy to implement modifications of the usual Slot Attention module, changing the value aggregation mechanism from a weighted mean operation to a scaled weighted sum operation.

Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In recent years, event cameras have gained significant attention due to their bio-inspired properties, such as high temporal resolution and high dynamic range. In this paper, we propose a novel approach for reconstructing such deformations using event measurements. Under the assumption of a static background, where all events are generated by the motion, our approach estimates the deformation of objects from events generated at the object contour in a probabilistic optimization framework. It associates events to mesh faces on the contour and maximizes the alignment of the line of sight through the event pixel with the associated face. In experiments on synthetic and real data of human body motion, we demonstrate the advantages of our method over state-of-the-art optimization and learning-based approaches for reconstructing the motion of human arms and hands. In addition, we propose an efficient event stream simulator to synthesize realistic event data for human motion.

Few-shot adaptation is an important capability for intelligent robots that perform tasks in open-world settings such as everyday environments or flexible production. In this paper, we propose a novel approach for non-prehensile manipulation which iteratively adapts a physics-based dynamics model for model-predictive control. We adapt the parameters of the model incrementally with a few examples of robot-object interactions. This is achieved by sampling-based optimization of the parameters using a parallelizable rigid-body physics simulation as dynamic world model. In turn, the optimized dynamics model can be used for model-predictive control using efficient sampling-based optimization. We evaluate our few-shot adaptation approach in several object pushing experiments in simulation and with a real robot.

Mobile robots should be capable of planning cost-efficient paths for autonomous navigation. Typically, the terrain and robot properties are subject to variations. For instance, properties of the terrain such as friction may vary across different locations. Also, properties of the robot may change such as payloads or wear and tear, e.g., causing changing actuator gains or joint friction. Autonomous navigation approaches should thus be able to adapt to such variations. In this article, we propose a novel approach for learning a probabilistic, terrain- and robot-aware forward dynamics model (TRADYN) which can adapt to such variations and demonstrate its use for navigation. Our learning approach extends recent advances in meta-learning forward dynamics models based on Neural Processes for mobile robot navigation. We evaluate our method in simulation for 2D navigation of a robot with uni-cycle dynamics with varying properties on terrain with spatially varying friction coefficients. In our experiments, we demonstrate that TRADYN has lower prediction error over long time horizons than model ablations which do not adapt to robot or terrain variations. We also evaluate our model for navigation planning in a model-predictive control framework and under various sources of noise. We demonstrate that our approach yields improved performance in planning control-efficient paths by taking robot and terrain properties into account.

Physics-based understanding of object interactions from sensory observations is an essential capability in augmented reality and robotics. It enables to capture the properties of a scene for simulation and control. In this paper, we propose a novel approach for real-to-sim which tracks rigid objects in 3D from RGB-D images and infers physical properties of the objects. We use a differentiable physics simulation as state-transition model in an Extended Kalman Filter which can model contact and friction for arbitrary mesh-based shapes and in this way estimate physically plausible trajectories. We demonstrate that our approach can filter position, orientation, velocities, and concurrently can estimate the coefficient of friction of the objects. We analyze our approach on various sliding scenarios in synthetic image sequences of single objects and colliding objects. We also demonstrate and evaluate our approach on a real-world dataset. We make our novel benchmark datasets publicly available to foster future research in this novel problem setting and comparison with our method.

Humans are proficient at intuitively identifying objects and reasoning about their diverse properties from complex visual observations. Despite significant advances in artificial intelligence, computers have yet to achieve a comparable level of understanding, which is crucial for effective reasoning about tasks and interactions within an environment. In this thesis, we explore the benefits of various visual cues when dealing with key challenges in scene understanding, specifically focusing on weak supervision, finding view correspondence, and paradigms for simultaneously learning multiple tasks. We begin by investigating cues that reduce the need for full supervision. In particular, we propose an approach for learning multi-object 3D scene decomposition and object-wise properties from single images with only weak supervision. Our method utilizes a recurrent encoder to infer a latent representation for each object and a differentiable renderer to obtain a training signal. To guide the training process and constrain the search space of possible solutions, we leverage prior knowledge through pre-trained 3D shape spaces. Subsequently, we investigate the benefits of reasoning about relations between objects to learn more distinct object representations that allow for matching object detections across viewpoint changes. To address this, we introduce an approach that employs graph neural networks to learn matching features based on appearance as well as inter- and cross-frame relations. We conduct comparisons with keypoint-based methods and propose a methodology to combine these approaches, aiming to achieve overall improved performance. Finally, we consider the challenge of multi-task learning and analyze related paradigms in the context of basic single-task learning. In particular, we study the impact of the choice of optimizer, the role of gradient conflicts, and the effects on the transferability of features learned through either learning setup on common image corruptions. Our findings reveal surprising similarities between single-task and multi-task learning, suggesting that methods and techniques from one field could be advantageously applied to the other.

Learning-based methods for sequential decision making, i.e., methods which leverage data, have shown the ability to solve complex problems in recent years. This includes control of dynamical systems, as well as mastering games such as Go and StarCraft. In addition, these methods often promise to be applicable to a wide variety of problems. A subclass of these methods are model-based methods. They leverage data to learn a model which allows predicting the evolution of a dynamical system to control. In recent research, it was shown that these methods, in contrast to model-free methods, require less data to be trained. In addition, model-based methods allow re-using the dynamics model when the task to be solved has changed, and straightforward adaptation to changes in the system’s dynamics. One particular focus of this thesis is on learning dynamics models which can data-efficiently adapt to changes in the system’s dynamics, as well as the efficient collection of data to adapt a learned model. In this regard, two novel methods are presented. In the application domain of autonomous robot navigation, in which both parameters of the robot and the terrain are subject to change, a novel method comprising an adaptive dynamics model is presented and evaluated on a simulated environment. A further advantage of model-based methods is the ability to incorporate physical prior knowledge for model design. In this thesis, we demonstrate that leveraging physical prior knowledge is advantageous for the task of tracking and predicting the motion of a table tennis ball, respecting its spin. However, model-based methods, in particular planning with learned models, have to cope with certain challenges. For long prediction horizons, which are required if the effect of an action is apparent only far in the future, model errors accumulate. In addition, model-based planning is commonly computationally intensive, which is problematic if high-frequency, reactive control is required. In this thesis, a method is presented to alleviate these problems. To this end, we propose a two-layered hierarchical method. Model-based planning is only applied on the higher layer on symbolic abstractions. On the lower-layer, model-free reactive control is used. We show successful application of this method to board games which can only be interacted with through a robotic manipulator, e.g., a robotic arm, which requires high-frequency reactive control.

In autonomous navigation settings, several quantities can be subject to variations. Terrain properties such as friction coefficients may vary over time depending on the location of the robot. Also, the dynamics of the robot may change due to, e.g., different payloads, changing the system's mass, or wear and tear, changing actuator gains or joint friction. An autonomous agent should thus be able to adapt to such variations. In this paper, we develop a novel probabilistic, terrain- and robot-aware forward dynamics model, termed TRADYN, which is able to adapt to the above-mentioned variations. It builds on recent advances in meta-learning forward dynamics models based on Neural Processes. We evaluate our method in a simulated 2D navigation setting with a unicycle-like robot and different terrain layouts with spatially varying friction coefficients. In our experiments, the proposed model exhibits lower prediction error for the task of long-horizon trajectory prediction, compared to non-adaptive ablation models. We also evaluate our model on the downstream task of navigation planning, which demonstrates improved performance in planning control-efficient paths by taking robot and terrain properties into account.

Intelligent robots require object-level scene understanding to reason about possible tasks and interactions with the environment. Moreover, many perception tasks such as scene reconstruction, image retrieval, or place recognition can benefit from reasoning on the level of objects. While keypoint-based matching can yield strong results for finding correspondences for images with small to medium view point changes, for large view point changes, matching semantically on the object-level becomes advantageous. In this paper, we propose a learning-based approach which combines local keypoints with novel object-level features for matching object detections between RGB images. We train our object-level matching features based on appearance and inter-frame and cross-frame spatial relations between objects in an associative graph neural network. We demonstrate our approach in a large variety of views on realistically rendered synthetic images. Our approach compares favorably to previous state-of-the-art object-level matching approaches and achieves improved performance over a pure keypoint-based approach for large view-point changes.

Humans have the remarkable ability to perceive and interact with objects in the world around them. They can easily segment objects from visual data and have an intuitive understanding of how physics influences objects. By contrast, robots are so far often constrained to tailored environments for a specific task, due to their inability to reconstruct a versatile and accurate scene representation. In this thesis, we combine RGB-D video data with background knowledge of real-world physics to develop such a representation for robots.</br> </br> Our contributions can be separated into two main parts: a dynamic object tracking tool and optimization frameworks that allow for improving shape reconstructions based on physical plausibility. The dynamic object tracking tool "EM-Fusion" detects, segments, reconstructs, and tracks objects from RGB-D video data. We propose a probabilistic data association approach for attributing the image pixels to the different moving objects in the scene. This allows us to track and reconstruct moving objects and the background scene with state-of-the art accuracy and robustness towards occlusions.</br> </br> We investigate two ways of further optimizing the reconstructed shapes of moving objects based on physical plausibility. The first of these, "Co-Section", includes physical plausibility by reasoning about the empty space around an object. We observe that no two objects can occupy the same space at the same time and that the depth images in the input video provide an estimate of observed empty space. Based on these observations, we propose intersection and hull constraints, which we combine with the observed surfaces in a global optimization approach. Compared to EM-Fusion, which only reconstructs the observed surface, Co-Section optimizes watertight shapes. These watertight shapes provide a rough estimate of unseen surfaces and could be useful as initialization for further refinement, e.g., by interactive perception. In the second optimization approach, "DiffSDFSim", we reason about object shapes based on physically plausible object motion. We observe that object trajectories after collisions depend on the object's shape, and extend a differentiable physics simulation for optimizing object shapes together with other physical properties (e.g., forces, masses, friction) based on the motion of the objects and their interactions. Our key contributions are using signed distance function models for representing shapes and a novel method for computing gradients that models the dependency of the time of contact on object shapes. We demonstrate that our approach recovers target shapes well by fitting to target trajectories and depth observations. Further, the ground-truth trajectories are recovered well in simulation using the resulting shape and physical properties. This enables predictions about the future motion of objects by physical simulation.</br> </br> We anticipate that our contributions can be useful building blocks in the development of 3D environment perception for robots. The reconstruction of individual objects as in EM-Fusion is a key ingredient required for interactions with objects. Completed shapes as the ones provided by Co-Section provide useful cues for planning interactions like grasping of objects. Finally, the recovery of shape and other physical parameters using differentiable simulation as in DiffSDFSim allows simulating objects and thus predicting the effects of interactions. Future work might extend the presented works for interactive perception of dynamic environments by comparing these predictions with observed real-world interactions to further improve the reconstructions and physical parameter estimations.

Implementing dynamic locomotion behaviors on legged robots requires a high-quality state estimation module. Especially when the motion includes flight phases, state-of-the-art approaches fail to produce reliable estimation of the robot posture, in particular base height. In this paper, we propose a novel approach for combining visual-inertial odometry (VIO) with leg odometry in an extended Kalman filter (EKF) based state estimator. The VIO module uses a stereo camera and IMU to yield low-drift 3D position and yaw orientation and drift-free pitch and roll orientation of the robot base link in the inertial frame. However, these values have a considerable amount of latency due to image processing and optimization, while the rate of update is quite low which is not suitable for low-level control. To reduce the latency, we predict the VIO state estimate at the rate of the IMU measurements of the VIO sensor. The EKF module uses the base pose and linear velocity predicted by VIO, fuses them further with a second high-rate IMU and leg odometry measurements, and produces robot state estimates with a high frequency and small latency suitable for control. We integrate this lightweight estimation framework with a nonlinear model predictive controller and show successful implementation of a set of agile locomotion behaviors, including trotting and jumping at varying horizontal speeds, on a torque-controlled quadruped robot.

Visual-inertial odometry (VIO) is an important technology for autonomous robots with power and payload constraints. In this paper, we propose a novel approach for VIO with stereo cameras which integrates and calibrates the velocity-control based kinematic motion model of wheeled mobile robots online. Including such a motion model can help to improve the accuracy of VIO. Compared to several previous approaches proposed to integrate wheel odometer measurements for this purpose, our method does not require wheel encoders and can be applied when the robot motion can be modeled with velocity-control based kinematic motion model. We use radial basis function (RBF) kernels to compensate for the time delay and deviations between control commands and actual robot motion. The motion model is calibrated online by the VIO system and can be used as a forward model for motion control and planning. We evaluate our approach with data obtained in variously sized indoor environments, demonstrate improvements over a pure VIO method, and evaluate the prediction accuracy of the online calibrated model.

Representing scenes at the granularity of objects is a prerequisite for scene understanding and decision making. We propose PriSMONet, a novel approach based on Prior Shape knowledge for learning Multi-Object 3D scene decomposition and representations from single images. Our approach learns to decompose images of synthetic scenes with multiple objects on a planar surface into its constituent scene objects and to infer their 3D properties from a single view. A recurrent encoder regresses a latent representation of 3D shape, pose and texture of each object from an input RGB image. By differentiable rendering, we train our model to decompose scenes from RGB-D images in a self-supervised way. The 3D shapes are represented continuously in function-space as signed distance functions which we pre-train from example shapes in a supervised way. These shape priors provide weak supervision signals to better condition the challenging overall learning task. We evaluate the accuracy of our model in inferring 3D scene layout, demonstrate its generative capabilities, assess its generalization to real images, and point out benefits of the learned representation.

Visual reconstruction of fast non-rigid object deformations over time is a challenge for conventional frame-based cameras. In this paper, we propose a novel approach for reconstructing such deformations using measurements from event-based cameras. Our approach estimates the deformation of objects from events generated at the object contour in a probabilistic optimization framework. It associates events to mesh faces on the contour and maximizes the alignment of the line of sight through the event pixel with the associated face. In experiments on synthetic and real data, we demonstrate the advantages of our method over state-of-the-art optimization and learning-based approaches for reconstructing the motion of human hands.

Problems which require both long-horizon planning and continuous control capabilities pose significant challenges to existing reinforcement learning agents. In this paper we introduce a novel hierarchical reinforcement learning agent which links temporally extended skills for continuous control with a forward model in a symbolic discrete abstraction of the environment’s state for planning. We term our agent SEADS for Symbolic Effect-Aware Diverse Skills. We formulate an objective and corresponding algorithm which leads to unsupervised learning of a diverse set of skills through intrinsic motivation given a known state abstraction. The skills are jointly learned with the symbolic forward model which captures the effect of skill execution in the state abstraction. After training, we can leverage the skills as symbolic actions using the forward model for long-horizon planning and subsequently execute the plan using the learned continuous-action control skills. The proposed algorithm learns skills and forward models that can be used to solve complex tasks which require both continuous control and long-horizon planning capabilities with high success rate. It compares favorably with other flat and hierarchical reinforcement learning baseline agents and is successfully demonstrated with a real robot.

In this paper, we analyze the observability of the visual-inertial odometry (VIO) using stereo cameras with a velocity-control based kinematic motion model. Previous work shows that in general case the global position and yaw are unobservable in VIO system, additionally the roll and pitch become also unobservable if there is no rotation. We prove that by integrating a planar motion constraint roll and pitch become observable. We also show that the parameters of the motion model are observable.

In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transitions of the respective system. The probabilistic formulation allows us to compute an action sequence which, for a limited number of environment interactions, optimally explores the given system within the parametrized family. This is achieved by steering the system through transitions being most informative for the context variable. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments.

Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy Method (CEM), can yield compelling results even in high-dimensional control tasks and sparse-reward environments. However, their sampling inefficiency prevents them from being used for real-time planning and control. We propose an improved version of the CEM algorithm for fast planning, with novel additions including temporally-correlated actions and memory, requiring 2.7-22x less samples and yielding a performance increase of 1.2-10x in high-dimensional control problems.

Cameras and inertial measurement units are complementary sensors for ego-motion estimation and environment mapping. Their combination makes visual-inertial odometry (VIO) systems more accurate and robust. For globally consistent mapping, however, combining visual and inertial information is not straightforward. To estimate the motion and geometry with a set of images large baselines are required. Because of that, most systems operate on keyframes that have large time intervals between each other. Inertial data on the other hand quickly degrades with the duration of the intervals and after several seconds of integration, it typically contains only little useful information. In this paper, we propose to extract relevant information for visual-inertial mapping from visual-inertial odometry using non-linear factor recovery. We reconstruct a set of non-linear factors that make an optimal approximation of the information on the trajectory accumulated by VIO. To obtain a globally consistent map we combine these factors with loop-closing constraints using bundle adjustment. The VIO factors make the roll and pitch angles of the global map observable, and improve the robustness and the accuracy of the mapping. In experiments on a public benchmark, we demonstrate superior performance of our method over the state-of-the-art approaches.