ICRA 2023 Papers

Human supervisors in multi-robot systems are primarily responsible for monitoring robots, but can also be assigned with secondary tasks. These tasks can act as interruptions and can be categorized as either intrinsic, i.e., being directly related to the monitoring task, or extrinsic, i.e., being unrelated. In this paper, we investigate the impact of these two types of interruptions through a user study (N = 39), where participants monitor a number of remote mobile robots while intermittently being interrupted by either a robot fault correction task (intrinsic) or a messaging task (extrinsic). We find that task performance of participants does not change significantly with the interruptions but depends greatly on the number of robots. However, interruptions result in an increase in perceived workload, and extrinsic interruptions have a more negative effect on workload across all NASA-TLX scales. Participants also reported switching between extrinsic interruptions and the primary task to be more difficult compared to the intrinsic interruption case. Statistical significance of these results is confirmed using ANOVA and one-sample t-test. These findings suggest that when deciding task assignment in such supervision systems, one should limit interruptions from secondary tasks, especially extrinsic ones, in order to limit user workload.

This paper discusses the effect of axial backbone compression on tendon-driven continuum robots. A new mechanics model for compensating for this effect that does not require tendon tension sensing or knowledge of manipulator material properties/stiffnesses is introduced and analyzed. In addition, we provide an analytical expression for the minimum preload on the tendons to achieve a given bend, a quantity determined empirically thus far. Our model is computationally efficient and achieves real time control on low cost hardware. The analysis is supported by experimental results demonstrating significant improvement over kinematics in open loop control of a tendon-driven continuum hose robot.

For a given set of orbits, the Orbiting Dubins Traveling Salesman Problem (ODTSP) involves finding Dubins tour that is tangential to each orbit at some point. We consider a shortest Arc-to-Arc Dubins (ATAD) path problem that arrives in solving lower bound to the ODTSP. Given an initial and a final arc, the objective of ATAD is to find the shortest Dubins path such that the initial and final point lie on the given two arcs, and the path is tangential to the arcs. We analyze the six Dubins modes and the degenerate cases to find local minima. We present the optimal solution for the ATAD, along with an algorithm that uses this solution to compute tight lower bounds for the ODTSP. We test the lower bounding algorithm on several random instances and report the results. Using this algorithm, we show that the percent gap between upper and lower bounds is less than 10% for most instances.

This paper presents two methods for the computation of the null space velocity command in redundant robots. Both these methods resort to the solution of a constrained optimization problem. The first one is a formalization of the traditional Gradient Projection Method (GPM) which guarantees the respect of the joint bounds and a gradual activation/deactivation of the null space command. The second one, called Null Space Basis Optimal Linear Combination Method (NSBM), finds the optimal coefficients of a basis of the null space of the Jacobian, ensuring in turn that the joint bounds are respected and that the null space is activated and deactivated gradually. The two methods are applied to the case study of a welding application in which the null space command must avoid the collision between the robot and an obstacle. The comparison of the results of the case study shows that NSBM performs better than GPM. The proposed algorithms are also tested on a real robotic platform to demonstrate that their computational time is compatible with the real-time requirements of the robot.

Legible motion is intent-expressive, which when employed during social robot navigation, allows others to quickly infer the intended avoidance strategy. Predictable motion matches an observer's expectation which, during navigation, allows others to confidently carryout the interaction. In this work, we present a navigation framework capable of reasoning on its legibility and predictability with respect to dynamic interactions, e.g., a passing side. Our approach generalizes the previously formalized notions of legibility and predictability by allowing dynamic goal regions in order to navigate in dynamic environments. This generalization also allows us to quantitatively evaluate the legibility and the predictability of trajectories with respect to navigation interactions. Our approach is shown to promote legible behavior in ambiguous scenarios and predictable behavior in unambiguous scenarios. In a multi-agent environment, this yields an increase in safety while remaining competitive in terms of goal-efficiency when compared to other robot navigation planners in multi-agent environments. The code of this work is made publicly available1.

Instance segmentation is a long-standing task for supporting robotic bin picking. However, objects of diverse classes can be closely packed with occlusions in cluttered and chaotic scenes, hence, even recent methods could have difficulty in locating clear and precise boundaries to distinguish nearby objects. In this work, we aim to improve the boundary quality of the instance masks for robust and precise instance segmentation in these challenging scenarios. Technical-wise, we first formulate an IoU-based Boundary-aware Mask head (IBM head) for predicting the instance-level mask, boundary, and their corresponding IoU scores. With this core module, we then follow the coarse-to-fine strategy and design our pipeline with two stages: an 1IoUNet to learn localization-based objectness cue and a hierarchical mask refiner to produce sharper and cleaner boundaries. We deploy the IBM head throughout the framework. Extensive experimental results on three grasping benchmarks manifest that our method attains the best instance segmentation performance, compared with the state-of-the-art approaches. Practically, we conduct real-world picking tests to show that with the objectness and boundary IoU scores as guidance, we are able to filter invalid (occluded) instances and select high-fidelity (exposed) instances for grasping.

The advancement in robotic grasping and manipulation has elicited an increased research interest in the development of household robots capable of performing a plethora of complex tasks. These advancements require the shift of robotics research from a laboratory setting to dynamic and unstructured home environments. In this work, we focus on a comprehensive data collection and analysis of key attributes involved in the selection of grasping and manipulation strategies for the successful execution of kitchen tasks. An unprecedented dataset that comprises over 7 hours of high-definition videos that were analyzed to classify more than 10,000 kitchen activities annotated with 24 attributes each has been created. Machine learning techniques were employed to automate the annotation process partially by extracting grasp types, hand, and object information from the videos. The annotated dataset was analyzed using clustering algorithms to identify underlying patterns. This study also identifies key attributes and specific data that require focus during data collection based on inter-subject variability. The insights from this study can be used to improve the speed, quality, and effectiveness of data collection. It also helps identify the strategies employed by the humans for the execution of kitchen tasks and transfer the necessary skills to a robotic end-effector enabling it to complete the tasks autonomously or collaborate with humans.

Agricultural robots have the prospect to enable more efficient and sustainable agricultural production of food, feed, and fiber. Perception of crops and weeds is a central component of agricultural robots that aim to monitor fields and assess the plants as well as their growth stage in an automatic manner. Semantic perception mostly relies on deep learning using supervised approaches, which require time and qualified workers to label fairly large amounts of data. In this paper, we look into the problem of reducing the amount of labels without compromising the final segmentation performance. For robots operating in the field, pre-training networks in a supervised way is already a popular method to reduce the number of required labeled images. We investigate the possibility of pre-training in a self-supervised fashion using data from the target domain. To better exploit this data, we propose a set of domain-specific augmentation strategies. We evaluate our pre-training on semantic segmentation and leaf instance segmentation, two important tasks in our domain. The experimental results suggest that pre-training with domain-specific data paired with our data augmentation strategy leads to superior performance compared to commonly used pre-trainings. Furthermore, the pre-trained networks obtain similar performance to the fully supervised with less labeled data.

Recently, various successful applications utilizing expert states in imitation learning (IL) have been witnessed. However, IL from visual inputs (ILfVI), which has a greater promise to be widely applied by using online visual resources, suffers from low data-efficiency and poor performance resulted from on-policy learning and high-dimensional visual inputs. We propose OPIfVI (Off-Policy Imitation from Visual Inputs), which is composed of an off-policy learning manner, data augmentation, and encoder techniques, to tackle the mentioned challenges, respectively. More specifically, to improve data-efficiency, OPIfVI conducts IL in an off-policy manner, with which sampled data used multiple times. In addition, we enhance the stability of OPIfVI with spectral normalization to mitigate the side effect of off-policy training. The core factor, contributing to the poor performance of ILfVI, that we think is agents could not extract meaningful features from visual inputs. Hence, OPIfVI employs data augmentation from computer vision to help train encoders to better extract features from visual inputs. Besides, a specific structure of gradient backpropagation for the encoder is designed to stabilize the encoder training. At last, we demonstrate that OPIfVI can achieve expert-level performance and outperform existing baselines via extensive experiments using DeepMind Control Suite.

Autonomous navigation in crowded spaces poses a challenge for mobile robots due to the highly dynamic, partially observable environment. Occlusions are highly prevalent in such settings due to a limited sensor field of view and obstructing human agents. Previous work has shown that observed interactive behaviors of human agents can be used to estimate potential obstacles despite occlusions. We propose integrating such social inference techniques into the planning pipeline. We use a variational autoencoder with a specially designed loss function to learn representations that are meaningful for occlusion inference. This work adopts a deep reinforcement learning approach to incorporate the learned representation into occlusion-aware planning. In simulation, our occlusion-aware policy achieves comparable collision avoidance performance to fully observable navigation by estimating agents in occluded spaces. We demonstrate successful policy transfer from simulation to the real-world Turtlebot 2i. To the best of our knowledge, this work is the first to use social occlusion inference for crowd navigation. Our implementation is available at https://github.com/yejimun/PaS_CrowdNav.

In this work, we present a method to extract the skeleton of a self-occluded tree canopy by estimating the unobserved structures of the tree. A tree skeleton compactly describes the topological structure and contains useful information such as branch geometry, positions and hierarchy. This can be critical to planning contact interactions for agricultural manipulation, yet is difficult to gain due to occlusion by leaves, fruits and other branches. Our method uses an instance segmentation network to detect visible trunk, branches, and twigs. Then, based on the observed tree structures, we build a custom 3D likelihood map in the form of an occupancy grid to hypothesize on the presence of occluded skeletons through a series of minimum cost path searches. We show that our method outperforms baseline methods in highly occluded scenes, demonstrated through a set of experiments on a synthetic tree dataset. Qualitative results are also presented on a real tree dataset collected from the field.

In this paper, we propose a novel mapping-planning framework for autonomous quadrotor navigation. First, a polyhedron-based mapping algorithm is presented to fully exploit the information of the onboard sensor data. Polyhedra are generated to approximate the segmented clusters of occupied voxels. Then, customized data structures are designed to extract information for motion planning in real time. With complete knowledge of the shape, position, and number of the observed obstacles, we can conveniently generate smooth trajectories with sufficient obstacle clearance along the most desired direction. Before searching for the initial path, a local topological graph is constructed to keep the path expanding in the most favorable topology class. The following path search is segmented based on the graph vertices, which allows fast convergence. The refined trajectory is obtained after smoothing, and large deviations are penalized in the formulated optimization problem to preserve the original clearance. Finally, we analyze and validate the proposed framework through extensive simulations and real-world quadrotor flights.

This paper presents a novel method for using Riemannian Motion Policies on volumetric maps, shown in the example of obstacle avoidance for Micro Aerial Vehicles (MAVs), Today, most robotic obstacle avoidance algorithms rely on sampling or optimization-based planners with volumetric maps. However, they are computationally expensive and often have inflexible monolithic architectures. Riemannian Motion Policies are a modular, parallelizable, and efficient navigation alternative but are challenging to use with the widely used voxel-based environment representations. We propose using GPU raycasting and tens of thousands of concurrent policies to provide direct obstacle avoidance using Riemannian Motion Policies in voxelized maps without needing map smoothing or pre-processing. Additionally, we present how the same method can directly plan on LiDAR scans without any intermediate map. We show how this reactive approach compares favorably to traditional planning methods and can evaluate up to 200 million rays per second. We demonstrate the planner successfully on a real MAV for static and dynamic obstacles. The presented planner is made available as an open-source package11https://github.com/ethz-asl/reactive_avoidance.

Collision avoidance in the presence of dynamic obstacles in unknown environments is one of the most critical challenges for unmanned systems. In this paper, we present a method that identifies obstacles in terms of ellipsoids to estimate linear and angular obstacle velocities. Our proposed method is based on the idea of any object can be approximately expressed by ellipsoids. To achieve this, we propose a method based on variational Bayesian estimation of Gaussian mixture model, the Kyachiyan algorithm, and a refinement algorithm. Our proposed method does not require knowledge of the number of clusters and can operate in real-time, unlike existing optimization-based methods. In addition, we define an ellipsoid-based feature vector to match obstacles given two timely close point frames. Our method can be applied to any environment with static and dynamic obstacles, including ones with rotating obstacles. We compare our algorithm with other clustering methods and show that when coupled with a trajectory planner, the overall system can efficiently traverse unknown environments in the presence of dynamic obstacles.

The extrinsic parameters play a crucial role in multi-sensor fusion, such as visual-inertial Simultaneous Localization and Mapping(SLAM), as they enable the accurate alignment and integration of measurements from different sensors. However, extrinsic calibration is challenging in scenarios, such as underwater, where in-view structures are scanty and visibility is limited, causing incorrect extrinsic calibration due to insufficient motion on all degrees of freedom. In this paper, we propose an entropy-based active extrinsic calibration algorithm leverages observability analysis and information entropy to enhance the accuracy and reliability of extrinsic calibration. It determines the system observability numerically by using singular value decomposition (SVD) of the Fisher Information Matrix (FIM). Furthermore, when the extrinsic parameter is not fully observable, our method actively searches for the next best motion to recover the system's observability via entropy-based optimization. Experimental results on synthetic data, in a simulation, and using an actual underwater vehicle verify that the proposed method is able to avoid the calibration failure while improving the calibration accuracy and reliability.

This paper proposes an algorithm for generating Pareto-optimal privacy-aware trajectories for multi-robot coverage. Our approach utilizes a genetic algorithm to generate a set of modified trajectories for a team of robots that wishes to obscure its goal from an observer. A novel velocity-constrained crossover algorithm ensures all child trajectories are feasible for a holonomic vehicle. The Pareto front of generated trajectories allows a team to select an allowable trade-off between privacy and coverage cost given within their task. Simulation results demonstrate the performance of our algorithm in Voronoi-based coverage control. We show our approach successfully obscures the objective from our proposed observer.

Existence of symmetric objects, whose observation at different viewpoints can be identical, can deteriorate the performance of simultaneous localization and mapping (SLAM). This work proposes a system for robustly optimizing the pose of cameras and objects even in the presence of symmetric objects. We classify objects into three categories depending on their symmetry characteristics, which is efficient and effective in that it allows to deal with general objects and the objects in the same category can be associated with the same type of ambiguity. Then we extract only the unambiguous parameters corresponding to each category and use them in data association and joint optimization of the camera and object pose. The proposed approach provides significant robustness to the SLAM performance by removing the ambiguous parameters and utilizing as much useful geometric information as possible. Comparison with baseline algorithms confirms the superior performance of the proposed system in terms of object tracking and pose estimation, even in challenging scenarios where the baseline fails.

3D object reconfiguration encompasses common robot manipulation tasks in which a set of objects must be moved through a series of physically feasible state changes into a desired final configuration. Object reconfiguration is challenging to solve in general, as it requires efficient reasoning about environment physics that determine action validity. This information is typically manually encoded in an explicit transition system. Constructing these explicit encodings is tedious and error-prone, and is often a bottleneck for planner use. In this work, we explore embedding a physics simulator within a motion planner to implicitly discover and specify the valid actions from any state, removing the need for manual specification of action semantics. Our experiments demonstrate that the resulting simulation-based planner can effectively produce physically valid rearrangement trajectories for a range of 3D object reconfiguration problems without requiring more than an environment description and start and goal arrangements.

Radar sensors are emerging as solutions for perceiving surroundings and estimating ego-motion in extreme weather conditions. Unfortunately, radar measurements are noisy and suffer from mutual interference, which degrades the performance of feature extraction and matching, triggering imprecise matching pairs, which are referred to as outliers. To tackle the effect of outliers on radar odometry, aa novel outlier-robust method called ORORA is proposed, which is an abbreviation of Outlier-RObust RAdar odometry. To this end, a novel decoupling-based method is proposed, which consists of graduated non-convexity (GNC)-based rotation estimation and anisotropic component-wise translation estimation (A-COTE). Furthermore, our method leverages the anisotropic characteristics of radar measurements, each of whose uncertainty along the azimuthal direction is somewhat larger than that along the radial direction. As verified in the public dataset, it was demonstrated that our proposed method yields robust ego-motion estimation performance compared with other state-of-the-art methods. Our code is available at https://github.com/url-kaist/outlier-robust-radar-odometry.