Motion detection in 3D LiDAR is crucial for autonomous systems. While deep learning dominates Moving Object Segmentation (MOS), the potential of learning-free approaches remains underexplored. Unlike problems like semantic segmentation, motion can be explicitly modeled, potentially enabling efficient, interpretable, and computationally lightweight solutions. Motivated by this, we introduce a novel real-time, online, learning-free MOS method. We propose the novel Join Count Feature to extract motion cues from a local window of range images, and long-term filtering with efficient two-step association to enhance accuracy. Compared to learning-based models, we achieve superior precision and competitive IoU for saliently moving objects on SemanticKITTI. Further evaluation on HeLiMOS demonstrate stronger generalization by the proposed method across different LiDAR sensors. These results highlight the potential of learning-free methods for motion detection in 3D LiDAR data.

To economically deploy robotic manipulators the programming and execution of robot motions must be swift. To this end, we propose a novel, constraint-based method to intuitively specify sequential manipulation tasks and to compute time-optimal robot motions for such a task specification. Our approach follows the ideas of constraint-based task specification by aiming for a minimal and object-centric task description that is largely independent of the underlying robot kinematics. We transform this task description into a non-linear optimization problem. By solving this problem we obtain a (locally) time-optimal robot motion, not just for a single motion, but for an entire manipulation sequence. We demonstrate the capabilities of our approach in a series of experiments involving five distinct robot models, including a highly redundant mobile manipulator.

In this paper we propose a new model for sequential manipulation tasks that also considers robot dynamics and time-variant environments. From this model we automatically derive constraint-based controllers and use them as steering functions in a kinodynamic manipulation planner. The resulting plan is not a trajectory but a sequence of controllers that react online to disturbances. We validated our approach in simulation and on a real robot. In the experiments our approach plans and executes dual-robot manipulation tasks with online collision avoidance and reactions to estimates of object poses.

This paper introduces a Bayesian state estimator for contact-rich manipulation tasks with application in non-prehensile manipulation, industrial assembly or in-hand localization. The core idea of our approach is to explicitly model both the contact dynamics and a torque-based robot controller as part of the underlying system model. Our approach is capable of estimating the state of movable objects for various robot kinematics and geometries of robots and objects. This includes complex scenarios with multiple robots, multiple objects and articulated objects. We have validated our approach in simulation and on a physical robot. The experiments show that multimodal distributions of six degrees of freedom object poses can be accurately tracked in real-time in a complex manipulation scenario.

When robots perform manipulation tasks, they need to determine their own movement, as well as how to make and break contact with objects in their environment. Reasoning about the motions of robots and objects simultaneously leads to a constrained planning problem in a high-dimensional state-space. Additionally, when environments change dynamically motions must be computed in real-time. To this end, we propose a feedback planner for manipulation. We model manipulation as constrained motion and use this model to automatically derive a set of constraint-based controllers. These controllers are used in a switching-control scheme, where the active controller is chosen by a reinforcement learning agent. Our approach is capable of addressing tasks with second-order dynamics, closed kinematic chains, and time-variant environments. We validated our approach in simulation and on a real, dual-arm robot. Extensive simulation of three distinct robots and tasks show a significant increase in robustness compared to a previous approach.

In this paper, we present an approach to generate robot motions for robust parts assembly. The computation of motions for parts assembly usually requires an exact model of all relevant objects. Generating detailed object models, including friction and dynamics, is often complex and time-consuming, especially in the context of elastic parts. In addition, executing motions on real hardware will usually introduce further uncertainty. For this reason, we propose an approach that is inherently robust against model parameter uncertainties and unknown characteristics of elastic parts. Our planner explicitly takes into account the internal states of articulated objects, as well as uncertain model parameters, by constructing a search tree in the belief-parameter-space. It yields successful assembly motions from coarse object models and thus eliminates the need for detailed parameter tuning. We evaluated our approach with respect to four assembly tasks. Extensive simulations show that our planner significantly increases the success-rate compared to previous approaches. Numerous experiments on a real robot confirm the simulated results.

In automated manufacturing, robots must reliably assemble parts of various geometries and low tolerances. Ideally, they plan the required motions autonomously. This poses a substantial challenge due to high-dimensional state spaces and non-linear contact-dynamics. Furthermore, object poses and model parameters, such as friction, are not exactly known and a source of uncertainty. The method proposed in this paper models the task of parts assembly as a belief space planning problem over an underlying impedance-controlled, compliant system. To solve this planning problem we introduce an asymptotically optimal belief space planner by extending an optimal, randomized, kinodynamic motion planner to nondeterministic domains. Under an expansiveness assumption we establish probabilistic completeness and asymptotic optimality. We validate our approach in thorough, simulated and realworld experiments of multiple assembly tasks. The experiments demonstrate our planner's ability to reliably assemble objects, solely based on CAD models as input.

When robots perform manipulation tasks, they need to determine their own movement, as well as how to grasp and release an object. Reasoning about the motion of the robot and the object simultaneously leads to a multi-modal planning problem in a high-dimensional configuration space. In this paper we propose an asymptotically optimal manipulation planner. Our approach extends optimal sampling-based roadmap planners to efficiently explore the configuration space of the robot and the object. We prove probabilistic completeness and global, asymptotic optimality. Extensive simulations of a typical pick-and-place scenario show that our approach significantly outperforms a (nonoptimal) state-of-the-art approach. We implemented our planner on a real manipulator and were able to compute high quality solutions in less than a second.

Reliable precision grasping for unknown objects is a prerequisite for robots that work in the field of logistics, manufacturing and household tasks. The nature of this task requires a simultaneous solution of a mixture of sub-problems. These include estimating object properties, finding viable grasps and executing grasps without displacement. We propose to explicitly take perceptual uncertainty into account during grasp execution. The underlying object representation is a probabilistic signed distance field, which includes both signed distances to the surface and spatially interpretable variances. Based on this representation, we propose a two-stage grasp generation method, which is specifically designed for generating precision grasps. In order to evaluate the whole approach, we perform extensive real world grasping experiments on a set of hard-to-grasp objects. Our approach achieves 78% success rate and shows robustness to the placement orientation.

In this paper, we present an approach for the probabilistic fusion of 3D sensor measurements. Our fusion algorithm is based on truncated signed distance functions. It explicitly considers the measurement noise by modeling the surface using random variables. Furthermore, our proposed surface model provides an explicit estimation of the spatial uncertainty. The approach can be implemented on a GPU to achieve a high update performance and enable online updates of the model. The approach was evaluated in simulation and using real sensor data. In our experiments, we confirmed that it accurately estimates surfaces from noisy sensor data and that it provides a corresponding estimate of the uncertainty. We could also show that the approach is able to fuse measurements from sensors with different noise characteristics.

Reliable precision grasping is a pre-condition for manipulation tasks e.g. in assembly and packaging tasks. Especially for small and light objects robust grasping is extremely challenging since even slight errors in the object pose or dimensions lead to irreparable failures caused by unintended finger-object contacts. State of the art techniques address the problem of grasping in the presence of uncertainty only at the grasp planning stage. We regard grasping as a dynamic process that needs closed loop control to be robustly executed, and propose an approach to robustly perform precision grasps despite of the significant perceptual and actuation uncertainties we have to face in reality. We conduct extensive real world experiments with light and fragile objects of unknown dimensions. The result confirms that our uncertainty-aware closed-loop approach significantly improves the robustness.

In this paper, we propose a probabilistic method to generate abstract scene graphs for table-top scenes from 6D object pose estimates. We explicitly make use of task-specific context knowledge by encoding this knowledge as descriptive rules in Markov logic networks. Our approach to generate scene graphs is probabilistic: Uncertainty in the object poses is addressed by a probabilistic sensor model that is embedded in a data driven MCMC process. We apply Markov logic inference to reason about hidden objects and to detect false estimates of object poses. The effectiveness of our approach is demonstrated and evaluated in real world experiments.

In this paper, we propose a generalizable method that systematically combines data driven MCMC sampling and inference using rule-based context knowledge for data abstraction. In particular, we demonstrate the usefulness of our method in the scenario of building abstract semantic maps for indoor environments. The product of our system is a parametric abstract model of the perceived environment that not only accurately represents the geometry of the environment but also provides valuable abstract information which benefits highlevel robotic applications. Based on predefined abstract terms, such as “type” and “relation”, we define task-specific context knowledge as descriptive rules in Markov Logic Networks. The corresponding inference results are used to construct a prior distribution that aims to add reasonable constraints to the solution space of semantic maps. In addition, by applying a semantically annotated sensor model, we explicitly use context information to interpret the sensor data. Experiments on real world data show promising results and thus confirm the usefulness of our system.

In this paper we propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning. The result of this procedure is a probabilistic generative model of the environment defined over abstract concepts. It is well suited for higher-level reasoning and communication purposes. We demonstrate the effectiveness of the approach through real-world experiments.

One of the main challenges for service robots during operation lies in the handling of unavoidable uncertainties which originate from model and sensor inaccuracies and which are characteristic for realistic application scenarios. Robustness under real world conditions can only be achieved when the dominant uncertainties are explicitly represented and purposefully managed by the robot's control system. We therefore adopt a probabilistic approach in which perception is regarded as a sequential estimation process and follow a Bayesian filtering methodology. Under these assumptions probabilistic models of the robot's perception systems are key. In this paper we shortly describe a model based object recognition and localization system. However, we do not not focus on the 6D pose estimation procedure itself, but on the method to quantify and compute the uncertainty associated with it. We construct a Gaussian approximation of the resulting pose error using the implicit function theorem. It is then used as a proposal density for importance sampling. Our goal is to sample from the measurement model describing 6D object localization based on local features in a Bayesian filtering context.

The ability to recognize objects and to localize them precisely is essential in all service robotic applications. One of the main challenges for service robots during operation lies in the handling of unavoidable uncertainties which originate from model and sensor inaccuracies and are characteristic for realistic application scenarios. Robustness under real world conditions can only be achieved when the dominant uncertainties are explicitly represented and purposefully managed by the robot's control system. We therefore adopt a probabilistic approach in which environment perception over time is regarded as a sequential estimation process and follow a Bayesian filtering methodology. Under these assumptions probabilistic models of the robot's perception systems play a decisive role. In this paper we describe our object localization system which is based on local features and uses 3D models that are created in an off-line modeling process. A probabilistic model of the errors, which occur in the 6D localization based on local features, is directly derived from the pose reconstruction procedure. Experimental results from an household scenario illustrate the effectiveness of our approach.