IROS 2023 论文列表

Stretching the definition of the standard Sine profile allows building a generalized symmetric frequency-aware basis function that can be used to generate reference motion trajectories. Other profiles such as polynomials, sigmoid, and harmonic-based models can be equally used under the proposed technique. Despite being suitable at the level of any higher-order time derivative, in this study, the generic basis function is realized at the jerk level such that the generated signals adhere to the limitations of the driven motion system. Introducing suitable time shifts, replicas of basis functions can be obtained giving rise to B-spline like frequency-aware profiles that can be used to realize the actual motion under any desired kinematical constraints, which are neatly written to reduces the computation burden at the motion controller side. Utilizing mainly the frequency-aware B-spline profiles, frequency-dependent random walk motion is presented and used to collect information about the driven motion system to help in characterizing any position-dependent errors through the statistical means, i.e. Analysis of Variance, and Design of Experiments. This allows dividing the working space in which motion takes place into several spatial regions with preferred frequency contents. The effectiveness of these proposed profiles is shown through hardware experiments using a precision motion system.

Upright locomotion has many health benefits for patients with spinal cord injury. Passive gait orthoses, such as an isocentric reciprocal gait orthosis (IRGO), allow patients to walk by pushing themselves forward with forearm supports. To move the legs, the IRGO physically couples the motion of stance and swing leg through a linkage. Unfortunately, this locomotion is associated with high metabolic effort. To reduce the metabolic demand while maintaining the advantages of simplicity and low weight of an IRGO, we propose the extension of an IRGO with a single actuator directly integrated into the rocking mechanism and investigate the use of a Hybrid Zero Dynamics based controller to support the user. This is a time-invariant feedback controller, in which a stable reciprocal gait is designed by means of numerically optimized virtual constraints. We evaluate the feasibility of this approach in a sagittal plane model of the dynamic system. For a range of walking speeds and step lengths, we are able to show that the chosen approach has the potential to safely support impaired users walking with IRGOs. The obtained gaits were periodic, stable, maintained a minimal ground clearance and could be implemented with a driving torque of 50 Nm.

A new control paradigm using angular momentum and foot placement as state variables in the linear inverted pendulum model has expanded the realm of possibilities for the control of bipedal robots. This new paradigm, known as the ALIP model, has shown effectiveness in cases where a robot's center of mass height can be assumed to be constant or near constant as well as in cases where there are no non-kinematic restrictions on foot placement. Walking up and down stairs violates both of these assumptions, where center of mass height varies significantly within a step and the geometry of the stairs restrict the effectiveness of foot placement. In this paper, we explore a variation of the ALIP model that allows the length of the virtual pendulum formed by the robot's stance foot and center of mass to follow smooth trajectories during a step. We couple this model with a control strategy constructed from a novel combination of virtual constraint-based control and a model predictive control algorithm to stabilize a stair climbing gait that does not soley rely on foot placement. Simulations on a 20-degree of freedom model of the Cassie biped in the SimMechanics simulation environment show that the controller is able to achieve periodic gait.

Trajectory optimization problems for legged robots are commonly formulated with fixed contact schedules. These multi-phase Hybrid Trajectory Optimization (HTO) methods result in locally optimal trajectories, but the result depends heavily upon the predefined contact mode sequence. Contact-Implicit Optimization (CIO) offers a potential solution to this issue by allowing the contact mode to be determined throughout the trajectory by the optimization solver. However, CIO suffers from long solve times and convergence issues. This work combines the benefits of these two methods into one algorithm: Staged Contact Optimization (SCO). SCO tightens constraints on contact in stages, eventually fixing them to allow robust and fast convergence to a feasible solution. Results on a planar biped and spatial quadruped demonstrate speed and optimality improvements over CIO and HTO. These properties make SCO well suited for offline trajectory generation or as an effective tool for exploring the dynamic capabilities of a robot.

Trajectory guidance requires a leader robotic agent to assist a follower robotic agent to cooperatively reach the target destination. However, planning cooperation becomes difficult when the leader serves a family of different followers and has incomplete information about the followers. There is a need for learning and fast adaptation of different cooperation plans. We develop a Stackelberg meta-learning approach to address this challenge. We first formulate the guided trajectory planning problem as a dynamic Stackelberg game to capture the leader-follower interactions. Then, we leverage meta-learning to develop cooperative strategies for different followers. The leader learns a meta-best-response model from a prescribed set of followers. When a specific follower initiates a guidance query, the leader quickly adapts to the follower-specific model with a small amount of learning data and uses it to perform trajectory guidance. We use simulations to elaborate that our method provides a better generalization and adaptation per-formance on learning followers' behavior than other learning approaches. The value and the effectiveness of guidance are also demonstrated by the comparison with zero guidance scenarios11The simulation codes are available at https://github.com/yuhan16/Stackelberg-Meta-Learning..

Soft actuators offer compliant and safe interaction with an unstructured environment compared to their rigid counterparts. However, control of these systems is often challenging because they are inherently under-actuated, have infinite degrees of freedom (DoF), and their mechanical properties can change by unknown external loads. Existing works mainly relied on discretization and reduction, suffering from either low accuracy or high computational cost for real-time control purposes. Recently, we presented an infinite-dimensional feedback controller for soft manipulators modeled by partial differential equations (PDEs) based on the Cosserat rod theory. In this study, we examine how to implement this controller in real-time using only a limited number of actuators. To do so, we formulate a convex quadratic programming problem that tunes the feedback gains of the controller in real-time such that it becomes realizable by the actuators. We evaluated the controller's performance through experiments on a physical soft robot capable of planar motions and show that the actual controller implemented by the finite-dimensional actuators still preserves the stabilizing property of the desired infinite-dimensional controller. This research fills the gap between the infinite-dimensional control design and finite-dimensional actuation in practice and suggests a promising direction for exploring PDE-based control design for soft robots.

Spin plays a considerable role in table tennis, making a shot's trajectory harder to read and predict. However, the spin is challenging to measure because of the ball's high velocity and the magnitude of the spin values. Existing methods either require extremely high framerate cameras or are unreliable because they use the ball's logo, which may not always be visible. Because of this, many table tennis-playing robots ignore the spin, which severely limits their capabilities. This paper proposes an easily implementable and reliable spin estimation method. We developed a dotted-ball orientation estimation (DOE) method, that can then be used to estimate the spin. The dots are first localized on the image using a CNN and then identified using geometric hashing. The spin is finally regressed from the estimated orientations. Using our algorithm, the ball's orientation can be estimated with a mean error of 2.4° and the spin estimation has an relative error lower than 1%. Spins up to 175 rps are measurable with a camera of 350 fps in real time. Using our method, we generated a dataset of table tennis ball trajectories with position and spin, available on our project page. Project page: https://cogsys-tuebingen.github.io/spindoe/.

Our study focuses on mapless navigation in robotics, which involves navigating without an established obstacle map of the environment. Spiking Neural Networks (SNNs) have recently been applied to this task using Deep Reinforcement Learning (DRL), but face challenges in dynamic and partially observable environments, as well as inaccuracies in transmitted data. To overcome these issues, we propose a Multi-Critic DDPG with Spiking Memory (MC-DDPGSM) framework. Our approach introduces a spiking Gate Recurrent Unit layer (Spiking-GRU) to provide memory function and evaluates the state-action value with multi-critic networks. The experimental results demonstrate that our method achieves better performance (success rate, navigation distance, navigation time spent, and power consumption) in complex navigation tasks compared to the state-of-the-art approaches. Furthermore, our model can be transferred to unseen environments without the need for fine-tuning.

This paper presents a new method for generating speed profiles for autonomous vehicles using a Transformer-based network that predicts the coefficients of quintic polynomials. To train and validate the network, we curate a dataset of 500K simulated urban driving scenarios, where the ground truths are obtained by running offline model predictive control (MPC) optimization. We also present tailored loss functions to emulate MPC behavior and constrain upper-and-lower boundary conditions to provide feasible speed profiles. Extensive experimental results demonstrate the efficacy of the proposed method in providing high-quality speed profiles for a large number of path candidates and long planning horizons. The proposed method is capable of generating efficient speed profiles for 1024 path candidates within 30ms.

This work focuses on the persistent monitoring problem, where a set of targets moving based on an unknown model must be monitored by an autonomous mobile robot with a limited sensing range. To keep each target's position estimate as accurate as possible, the robot needs to adaptively plan its path to (re-)visit all the targets and update its belief from measurements collected along the way. In doing so, the main challenge is to strike a balance between exploitation, i.e., re-visiting previously-located targets, and exploration, i.e., finding new targets or re-acquiring lost ones. Encouraged by recent advances in deep reinforcement learning, we introduce an attention-based neural solution to the persistent monitoring problem, where the agent can learn the inter-dependencies between targets, i.e., their spatial and temporal correlations, conditioned on past measurements. This endows the agent with the ability to determine which target, time, and location to attend to across multiple scales, which we show also helps relax the usual limitations of a finite target set with prior positional information. We experimentally demonstrate that our method outperforms other baselines in terms of number of targets visits and average estimation error in complex environments. Finally, we implement and validate our model in a drone-based simulation experiment to monitor mobile ground targets in a high-fidelity simulator.

In this paper, we propose using deep neural architectures (i.e., vision transformers and ResNet) as heuristics for sequential decision-making in robotic manipulation problems. This formulation enables predicting the subset of objects that are relevant for completing a task. Such problems are often addressed by task and motion planning (TAMP) formulations combining symbolic reasoning and continuous motion planning. In essence, the action-object relationships are resolved for discrete, symbolic decisions that are used to solve manipulation motions (e.g., via nonlinear trajectory optimization). However, solving long-horizon tasks requires consideration of all possible action-object combinations which limits the scalability of TAMP approaches. To overcome this combinatorial complexity, we introduce a visual perception module integrated with a TAMP-solver. Given a task and an initial image of the scene, the learned model outputs the relevancy of objects to accomplish the task. By incorporating the predictions of the model into a TAMP formulation as a heuristic, the size of the search space is significantly reduced. Results show that our framework finds feasible solutions more efficiently when compared to a state-of-the-art TAMP solver.

With the prevalence of multimodal learning, camera-LiDAR fusion has gained popularity in 3D object detection. Many fusion approaches have been proposed, falling into two main categories: sparse-only or dense-only, differentiated by their feature representation within the fusion module. We analyze these approaches within a shared taxonomy, identifying two key challenges: (1) Sparse-only methodologies maintain 3D geometric prior but fail to capture the semantic richness from camera data, and (2) Dense-only strategies preserve semantic continuity at the expense of precise geometric information derived from LiDAR. Upon analysis, we deduce that due to their respective architectural designs, some degree of information loss is inevitable. To counteract this loss, we introduce Sparse Dense Fusion (SD-Fusion), an innovative framework combining both sparse and dense fusion modules via the Transformer architecture. The simple yet effective fusion strategy enhances semantic texture and simultaneously leverages spatial structure data. Employing our SD-Fusion strategy, we assemble two popular methods with moderate performance, achieving a 4.3% increase in mAP and a 2.5% rise in NDS, thus ranking first in the nuScenes benchmark. Comprehensive ablation studies validate the effectiveness of our approach and empirically support our findings.

Piecewise-affine (PWA) systems are widely used for modeling and control of robotics problems including modeling contact dynamics. A common approach is to encode the control problem of the PWA system as a Mixed-Integer Convex Program (MICP), which can be solved by general-purpose off-the-shelf MICP solvers. To mitigate the scalability challenge of solving these MICP problems, existing work focuses on devising efficient and strong formulations of the problems, while less effort has been spent on exploiting their specific structure to develop specialized solvers. The latter is the theme of our work. We focus on efficiently handling one-hot constraints, which are particularly relevant when encoding PWA dynamics. We have implemented our techniques in a tool, Soy, which organically integrates logical reasoning, arithmetic reasoning, and stochastic local search. For a set of PWA control benchmarks, Soy solves more problems, faster, than two state-of-the-art MICP solvers.

This work proposes the use of conditional Generative Adversarial Networks (cGANs) for acoustic-based 3D reconstruction. Acoustics being the most reliable sensor modality in underwater domains is accompanied with the loss of elevation angle in its images. The challenge of recovering the missing dimension in acoustic images have pushed researchers to try various methods and approaches over the past years. cGANs being an image-to-image translation method makes it possible to learn a desired style, and transforms the data from one modality to another. This was applied here as a way of transforming an acoustic image into another form which contains the elevation characteristics, such as depth images. Depth images are hard to acquire underwater, thus data was generated synthetically and used for training and testing the deep learning model. As a way of performance enhancement, real data was collected for training a Cycle-GAN network in the aim of transferring the realistic style into the synthetically generated images. Simulation experiments were conducted to evaluate the system and find out the best experimental setup, which was then used to carry out the real experiment. The system performed dense 3D reconstruction of the scanned object and proved to be applicable in real environments.

Soft object manipulation tasks in domestic scenes pose a significant challenge for existing robotic skill learning techniques due to their complex dynamics and variable shape characteristics. Since learning new manipulation skills from human demonstration is an effective way for robot applications, developing prior knowledge of the representation and dynamics of soft objects is necessary. In this regard, we propose a pretrained soft object manipulation skill learning model, namely SoftGPT, that is trained using large amounts of exploration data, consisting of a three-dimensional heterogeneous graph representation and a GPT-based dynamics model. For each downstream task, a goal-oriented policy agent is trained to predict the subsequent actions, and SoftGPT generates the consequences of these actions. Integrating these two approaches establishes a thinking process in the robot's mind that provides rollout for facilitating policy learning. Our results demonstrate that leveraging prior knowledge through this thinking process can efficiently learn various soft object manipulation skills, with the potential for direct learning from human demonstrations.

Incorporating compliance into shape-changing displays can improve their wearability and actuation modalities. While recent advances in soft actuators highlight promising paths for soft shape-changing displays, these displays currently face some practical challenges of device failure and limited actuator displacement. A monolithic fabrication processes means the device is challenging to repair, for a single point of failure often renders the whole device ineffective. We have leveraged a modular hyperelastic bubble array layer to create a soft shape-changing skin. The modularity of this device allows for rapid repair of individual bubbles and fast prototyping, and the spherical, hyperelastic actuators enable an increase in degrees of freedom due to bubble-to-bubble interactions. Furthermore, we present a forward kinematic description of our device, incorporating these bubble-to-bubble interactions and the nonlinear instabilities unique to hyperelastic actuator inflation. We demonstrate the utility of this soft shape-changing skin as a haptic display that can be worn comfortably or applied to passive interactive objects such as a computer mouse.

In this paper we present a novel kinematic representation of a soft continuum robot to enable full shape estimation using a purely geometric solution. The kinematic representation involves using length varying piecewise constant curvature segments to describe the deformed shape of the robot. Based on this kinematic representation, we can use overlapping length sensors to estimate the shape of continuously deformable bodies without prior knowledge of the current loading conditions. We show an implementation that assumes one change in curvature along the length of a joint, using string potentiometers as an arc length sensor, and an orientation measurement from the tip of the continuum joint. For 56 randomized joint configurations, we estimate the shape of a 250 mm long continually deformable robot with less then 2.5 mm of average error. The average error is reported for each of the 10 different equally spaced points along the length, demonstrating the ability to accurately represent the full shape of the soft robot.

Robotic palpation shows significant potential to improve the accuracy and speed of tumor identification. How-ever, robotic palpation mechanisms often lack haptic feedback, making it difficult for the surgeon to identify variations in tissue stiffness. This paper presents a soft optical sensor integrated with a wearable haptic glove for tumor detection during robotic palpation. The sensor contains an array of optical waveguides that can detect the presence of tumors embedded within a tissue phantom. Detection of a tumor results in an optical loss from the waveguide signal, triggering proportional inflation of the soft microfluidic actuators in the glove. The glove consists of four modular actuators placed at the fingertips, each corresponding to a sensing location on the waveguide array. The inflation of each actuator is proportional to the incident loss on the palpation sensor array, which is dependent on tumor depth. Thus, the glove is capable of alerting the user to the location of tumors during remote palpation.

Growing robots based on the eversion principle are known for their ability to extend rapidly, from within, along their longitudinal axis, and, in doing so, reach deep into hitherto inaccessible, remote spaces. Despite many advantages, vine robots also present significant challenges, one of which is maintaining sensory payload at the tip without restricting the eversion process. A variety of tip mechanisms have been proposed by the robotics community, among them rounded caps of relatively complex construction that are not always compatible with functional hardware, such as sensors or navigation pouches, integrated with the main eversion structure. Moreover, many tip designs incorporate rigid materials, reducing the robot's flexibility and consequent ability to navigate through narrow openings. Here, we address these shortcomings and propose a design to overcome them: a soft, entirely fabric based, cylindrical cap that can easily be slipped onto the tip of vine robots. Having created a series of caps of different sizes and materials, an experimental study was conducted to evaluate our new design in terms of four key aspects: vine robot made from multiple layers of everting material, solid objects protruding from the vine robot, squeezability, and navigability. In all scenarios, we can show that our soft, flexible cap is robust in its ability to maintain its position and is capable of transporting payloads such as a camera across long distances. We also demonstrate that the robot's ability to move through restricted aperture openings and indeed its overall flexibility is virtually unhindered by the addition of our cap. The paper discusses the advantages of this design and gives further recommendations in relation to aspects of its engineering.