IROS 2022 Papers

The Robotic locomotion community is interested in optimal gaits for control. Based on the optimization criterion, however, there could be a number of possible optimal gaits. For example, the optimal gait for maximizing displacement with respect to cost is quite different from the maximum displacement optimal gait. Beyond these two general optimal gaits, we believe that the optimal gait should deal with various situations for high-resolution of motion planning, e.g., steering the robot or moving in “baby steps.” As the step size or steering ratio increases or decreases, the optimal gaits will slightly vary by the geometric relationship and they will form the families of gaits. In this paper, we explored the geometrical framework across these optimal gaits having different step sizes in the family via the Lagrange multiplier method. Based on the structure, we suggest an optimal locus generator that solves all related optimal gaits in the family instead of optimizing each gait respectively. By applying the optimal locus generator to two simplified swimmers in drag-dominated environments, we verify the behavior of the optimal locus generator.

For robots to successfully execute tasks as-signed to them, they must be capable of planning the right sequence of actions. These actions must be both optimal with respect to a specified objective and satisfy whatever constraints exist in their world. We propose an approach for robot task planning that is capable of planning the optimal sequence of grounded actions to accomplish a task given a specific objective function while satisfying all specified numerical constraints. Our approach accomplishes this by encoding the entire task planning problem as a single mixed integer convex program, which it then solves using an off-the-shelf Mixed Integer Program-ming solver. We evaluate our approach on several mobile manipulation tasks in both simulation and on a physical humanoid robot. Our approach is able to consistently produce optimal plans while accounting for all specified numerical constraints in the mobile manipulation tasks. Open-source implementations of the components of our approach as well as videos of robots executing planned grounded actions in both simulation and the physical world can be found at this url: https://adubredu.github.io/gtpmip

Machine vision is a critical subsystem for enabling robots to be able to perform a variety of tasks in orchard environments. However, orchards are highly visually complex environments, and computer vision algorithms operating in them must be able to contend with variable lighting conditions and background noise. Past work on enabling deep learning algorithms to operate in these environments has typically required large amounts of hand-labeled data to train a deep neural network or physically controlling the conditions under which the environment is perceived. In this paper, we train a neural network system in simulation only using simulated RGB data and optical flow. This resulting neural network is able to perform foreground segmentation of branches in a busy orchard environment without additional real-world training or using any special setup or equipment beyond a standard camera. Our results show that our system is highly accurate and, when compared to a network using manually labeled RGBD data, achieves significantly more consistent and robust performance across environments that differ from the training set.

During in-hand manipulation, robots must be able to continuously estimate the pose of the object in order to generate appropriate control actions. The performance of algorithms for pose estimation hinges on the robot's sensors being able to detect discriminative geometric object features, but previous sensing modalities are unable to make such measurements robustly. The robot's fingers can occlude the view of environment- or robot-mounted image sensors, and tactile sensors can only measure at the local areas of contact. Motivated by fingertip-embedded proximity sensors' robustness to occlusion and ability to measure beyond the local areas of contact, we present the first evaluation of proximity sensor based pose estimation for in-hand manipulation. We develop a novel two-fingered hand with fingertip-embedded optical time-of-flight proximity sensors as a testbed for pose estimation during planar in-hand manipulation. Here, the in-hand manipulation task consists of the robot moving a cylindrical object from one end of its workspace to the other. We demonstrate, with statistical significance, that proximity-sensor based pose estimation via particle filtering during in-hand manipulation: a) exhibits 50% lower average pose error than a tactile-sensor based baseline; b) empowers a model predictive controller to achieve 30% lower final positioning error compared to when using tactile-sensor based pose estimates.

Existing Deep Learning (DL) frameworks typically do not provide ready-to-use solutions for robotics, where very specific learning, reasoning, and embodiment problems exist. Their relatively steep learning curve and the different methodologies employed by DL compared to traditional approaches, along with the high complexity of DL models, which often leads to the need of employing specialized hardware accelerators, further increase the effort and cost needed to employ DL models in robotics. Also, most of the existing DL methods follow a static inference paradigm, as inherited by the traditional computer vision pipelines, ignoring active perception, which can be employed to actively interact with the environment in order to increase perception accuracy. In this paper, we present the Open Deep Learning Toolkit for Robotics (OpenDR). OpenDR aims at developing an open, non-proprietary, efficient, and modular toolkit that can be easily used by robotics companies and research institutions to efficiently develop and deploy AI and cognition technologies to robotics applications, providing a solid step towards addressing the aforementioned challenges. We also detail the design choices, along with an abstract interface that was created to overcome these challenges. This interface can describe various robotic tasks, spanning beyond traditional DL cognition and inference, as known by existing frameworks, incorporating openness, homogeneity and robotics-oriented perception e.g., through active perception, as its core design principles.

The ability to make good decisions in partially observed non-cooperative multi-agent scenarios is important for robots to interact effectively in human environments. A robust framework for such decision-making problems is the Interactive Partially Observable Markov Decision Processes (I-POMDPs), which explicitly models the other agents' beliefs up to a finite reasoning level in order to more accurately predict their actions. This paper proposes a new online approximate solver for I-POMDPs, called Interactive Nested Tree Monte-Carlo Planning (I-NTMCP), that combines Monte Carlo Tree Search with the finite nested-reasoning construction of I-POMDPs. Unlike existing full-width I-POMDP planners, I-NTMCP focuses planning on the set of beliefs at each nesting level which are reachable under an optimal policy and uses sampling to construct and update policies at each nesting level, online. This strategy enables I-NTMCP to plan effectively in significantly larger I-POMDP problems and to deeper reasoning levels than has previously been possible. We demonstrate I-NTMCP's effectiveness on two competitive environments. The results indicate that I-NTMCP can generate substantially better policies up to more than 50× faster than I-POMDP Lite - one of the fastest I-POMDP solvers today. In the pursuit-evasion domain, we show I-NTMCP can plan effectively in a complex problem with over 88K states, which is two orders of magnitude larger than existing I-POMDP planning benchmark problems.

Traditional approaches to manipulating the state of deformable linear objects (DLOs) - i.e., cables, ropes - rely on model-based planning. However, constructing an accurate dynamic model of a DLO is challenging due to the complexity of interactions and a high number of degrees of freedom. This renders the task of achieving a desired DLO shape particularly difficult and motivates the use of model-free alternatives, which while maintaining generality suffer from a high sample complexity. In this paper, we bridge the gap between these fundamentally different approaches and propose a framework that learns dynamic models of DLOs through trial-and-error interaction. Akin to model-based reinforcement learning (RL), we interleave learning and exploration to solve a 3D shape control task for a DLO. Our approach requires only a fraction of the interaction samples of the current state-of-the-art model-free RL alternatives to achieve superior shape control performance. Unlike offline model learning, our approach does not require expert knowledge for data collection, retains the ability to explore, and automatically selects relevant experience.

This paper introduces an Online Localisation and Colored Mesh Reconstruction (OLCMR) ROS perception architecture for ground exploration robots aiming to perform robust Simultaneous Localisation And Mapping (SLAM) in challenging unknown environments and provide an associated colored 3D mesh representation in real time. It is intended to be used by a remote human operator to easily visualise the mapped environment during or after the mission or as a development base for further researches in the field of exploration robotics. The architecture is mainly composed of carefully-selected open-source ROS implementations of a LiDAR-based SLAM algorithm alongside a colored surface reconstruction procedure using a point cloud and RGB camera images projected into the 3D space. The overall performances are evaluated on the Newer College handheld LiDAR-Vision reference dataset and on two experimental trajectories gathered on board of representative wheeled robots in respectively urban and countryside outdoor environments.

While the musculoskeletal humanoid has various biomimetic benefits, its complex modeling is difficult, and many learning control methods have been developed. However, for the actual robot, the hysteresis of its joint angle tracking is still an obstacle, and realizing target posture quickly and accurately has been difficult. Therefore, we develop a feedback control method considering the hysteresis. To solve the problem in feedback controls caused by the closed-link structure of the musculoskeletal body, we update a neural network representing the relationship between the error of joint angles and the change in target muscle lengths online, and realize target joint angles accurately in a few trials. We compare the performance of several configurations with various network structures and loss definitions, and verify the effectiveness of this study on an actual musculoskeletal humanoid, Musashi.

In this paper, we propose the online extrinsic correction method that effectively optimizes the extrinsic parameters of multi-camera systems used in visual SLAM. In the typical visual SLAM systems that use multi-camera settings, the intrinsic and extrinsic parameters of the cameras are calculated through offline calibration, which is used as the fixed constraints in online execution. However, the camera rig can be physically deformed by shock or vibration, and the deviation from the offline calibration parameters can adversely affect the accuracy of triangulation and pose estimation. Therefore, it is crucial to maintain the accurate calibration of the camera rigs continuously throughout the execution. The previous online calibration methods optimize the extrinsic camera parameters in a full degree of freedom(DoF) by minimizing the reprojection error, but the limited visual information available online may bias the resulting camera poses. From the observation that the cameras are mounted on a physical body and the patterns that the body can be deformed is restricted and not completely free, we propose to model the pattern of physical rig deformation by external forces in advance, and then use the pre-trained low-dimensional deformation model to robustly and accurately estimate the changed camera poses in real-time. The proposed method consists of two steps. First, the physical model of the camera system is constructed in a simulator and the actual deformations by various external disturbances are recorded, and the deformation patterns are modeled by a PCA algorithm to build a low-dimensional model. In online execution, the camera poses are updated by minimizing the reprojection errors of visual features within the pre-trained low-dimensional parameterization, instead of optimizing all camera poses independently. Through the experiments in synthetic environments, the proposed online extrinsic correction method shows that it produces more accurate and robust camera pos... Show More

Area coverage is crucial for robotics applications such as cleaning, painting, exploration, and inspections. Hinged reconfigurable robots have been introduced for these application domains to improve the area coverage performance. However, the existing coverage algorithms of hinged reconfigurable robots require improvements in the aspects; consideration of beyond a limited set of reconfigurable shapes, coordinated reconfiguration and navigation, and online decision-making. Therefore, this paper proposes a novel online Complete Coverage Path Planning (CCPP) method for a hinged reconfigurable robot. The proposed CCPP method is designed with two sub-methods, the Global Coverage Path Planning (GCPP) and Local Coverage Path Planning (LCPP). The GCPP method has been implemented, adapting a Glasius Bio-inspired Neural Network (GBNN) that performs online path planning considering a fixed shape for the robot. Obstacle regions that the GCPP would not adequately cover due to access constraints are covered by the LCPP method that considers concurrent reconfiguration and navigation of the robot. A genetic algorithm determines the reconfiguration parameters that ascertain collision-free coverage and access of obstacle regions. Experimental results validate that the proposed online CCPP method is effective in ascertaining the complete area coverage in heterogeneous environments, including dynamic workspaces. Furthermore, the deployment of the LCPP method can considerably improve the coverage.

A control barrier functions-based quadratic programming (CBF-QP) method has emerged as a controller synthesis tool to assure safety of autonomous systems owing to the appealing safe forward invariant set. However, the provable safety relies on a precisely described dynamic model, which is not always available in practice. Recent works leverage learning to compensate model uncertainty for a CBF controller. However, these approaches based on reinforcement learning or episodic learning are limited to dealing with time-invariant uncertainty. Also, the reinforcement learning approach learns the uncertainty offline, while episodic learning only updates the controller after a batch of data is available by the end of an episode. Instead, we propose a novel tuning extreme learning machine (tELM)-based CBF controller that can compensate time-variant and time-invariant model uncertainty adaptively in an online manner. We validate our approach's effectiveness in a simulation of an Adaptive Cruise Control (ACC) system.

The 3D Bin Packing Problem (3D-BPP) is one of the most demanded yet challenging problems in industry, where an agent must pack variable size items delivered in sequence into a finite bin with the aim to maximize the space utilization. It represents a strongly NP-Hard optimization problem such that no solution has been offered to date with high performance in space utilization. In this paper, we present a new reinforcement learning (RL) framework for a 3D-BPP solution for improving performance. First, a buffer is introduced to allow multi-item action selection. By increasing the degree of freedom in action selection, a more complex policy that results in better packing performance can be derived. Second, we propose an agnostic data augmentation strategy that exploits both bin item symmetries for improving sample efficiency. Third, we implement a model-based RL method adapted from the popular algorithm AlphaGo, which has shown superhuman performance in zero-sum games. Our adaptation is capable of working in single-player and score based environments. In spite of the fact that AlphaGo versions are known to be computationally heavy, we manage to train the proposed framework with a single thread and GPU, while obtaining a solution that outperforms the state-of-the-art results in space utilization.

LiDAR-based global localization is a fundamental problem for mobile robots. It consists of two stages, place recognition and pose estimation, which yields the current orientation and translation, using only the current scan as query and a database of map scans. Inspired by the definition of a recognized place, we consider that a good global localization solution should keep the pose estimation accuracy with a lower place density. Following this idea, we propose a novel framework towards sparse place-based global localization, which utilizes a unified and learning-free representation, Radon sinogram (RING), for all sub-tasks. Based on the theoretical derivation, a translation invariant descriptor and an orientation invariant metric are proposed for place recognition, achieving certifiable robustness against arbitrary orientation and large translation between query and map scan. In addition, we also utilize the property of RING to propose a global convergent solver for both orientation and translation estimation, arriving at global localization. Evaluation of the proposed RING based framework validates the feasibility and demonstrates a superior performance even under a lower place density.

A gaze-fixating robot perceives distance to the fixated object and relative positions of surrounding objects immediately, accurately, and robustly. We show how fixation, which is the act of looking at one object while moving, exploits regularities in the geometry of 3D space to obtain this information. These regularities introduce rotation-translation couplings that are not commonly used in structure from motion. To validate, we use a Franka Emika Robot with an RGB camera. We a) find that error in distance estimate is less than 5 mm at a distance of 15 cm, and b) show how relative position can be used to find obstacles under challenging scenarios. We combine accurate distance estimates and obstacle information into a reactive robot behavior that is able to pick up objects of unknown size, while impeded by unforeseen obstacles.

Robots have to take highly responsive real-time actions, driven by complex decisions involving a pipeline of sensing, perception, planning, and reaction tasks. These tasks must be scheduled on resource-constrained devices such that the performance goals and the requirements of the application are met. This is a difficult problem that requires handling multiple scheduling dimensions, and variations in computational resource usage and availability. In practice, system designers manually tune parameters for their specific hardware and application, which results in poor generalization and increases the development burden. In this work, we highlight the emerging need for scheduling CPU resources at runtime in robot systems. We use robot navigation as a case-study to understand the key scheduling requirements for such systems. Armed with this understanding, we develop a CPU scheduling framework, Catan, that dynamically schedules compute resources across different components of an app so as to meet the specified application requirements. Through experiments with a prototype implemented on ROS, we show the impact of system scheduling on meeting the application's performance goals, and how Catan dynamically adapts to runtime variations.

This paper analyzes the effect of control param-eters of feed-forward and inner loop velocity controller in an admittance control scheme on the performance and passivity. The interaction force, inertia, and damping compensation were considered as the feed-forward input. Sufficient conditions and guidelines for each parameter were provided to enable the implementation of a wide range of desired admittance satis-fying passivity. The proposed guidelines were verified through experiments.

Automated grasping of arbitrary objects is an essential skill for many applications such as smart manufacturing and human robot interaction. This makes grasp detection a vital skill for automated robotic systems. Recent work in model-free grasp detection uses point cloud data as input and typically outperforms the earlier work on RGB(D)-based methods. We show that RGB(D)-based methods are being underestimated due to suboptimal label encodings used for training. Using the evaluation pipeline of the GraspNet-1Billion dataset, we investigate different encodings and propose a novel encoding that significantly improves grasp detection on depth images. Additionally, we show shortcomings of the 2D rectangle grasps supplied by the GraspNet-1Billion dataset and propose a filtering scheme by which the ground truth labels can be improved significantly. Furthermore, we apply established methods for uncertainty estimation on our trained models since knowing when we can trust the model's decisions provides an advantage for real-world application. By doing so, we are the first to directly estimate uncertainties of detected grasps. We also investigate the applicability of the estimated aleatoric and epistemic uncertainties based on their theoretical properties. Additionally, we demonstrate the correlation between estimated uncertainties and grasp quality, thus improving selection of high quality grasp detections. By all these modifications, our approach using only depth images can compete with point-cloud-based approaches for grasp detection despite the lower degree of freedom for grasp poses in 2D image space.

Teleoperated robots are believed to play an important role for future applications in industry, medicine and other domains. Examples for this are remote assembly and maintenance, surgery, diagnosis or deep-sea and space exploration. Such applications are made possible by state-of-the-art tactile manipulators, well-researched control schemes and novel communication technologies such as the fifth generation of mobile communication (5G). The achievable performance is highly dependent on the communication delay and thus on the distance between leader and follower station, as well as the potentially used wireless protocol. Specially in this regard, 5G is a promising technology compared to the other communication protocols for transferring tactile information. In this paper, we introduce our telepresence reference platform, which can be used for empirical evaluation of different algorithms and communications. Comparative analysis are conducted to capture the influence of wireless communication protocols on telepresence systems consisting of complex robotic arms. The experiment compares the influence of 5G, LTE and WiFi communication protocols with regard to the motion and force tracking performance of the system.