ICRA 2024 Papers

Image matching is still challenging in such scenes with large viewpoints or illumination changes or with low textures. In this paper, we propose a Transformer-based pseudo 3D image matching method. It upgrades the 2D features extracted from the source image to 3D features with the help of a reference image and matches to the 2D features extracted from the destination image by the coarse-to-fine 3D matching. Our key discovery is that by introducing the reference image, the source image’s fine points are screened and furtherly their feature descriptors are enriched from 2D to 3D, which improves the match performance with the destination image. Experimental results on multiple datasets show that the proposed method achieves the state-of-the-art on the tasks of homography estimation, pose estimation and visual localization especially in challenging scenes.

We introduce a novel approach that combines tactile estimation and control for in-hand object manipulation. By integrating measurements from robot kinematics and an image-based tactile sensor, our framework estimates and tracks object pose while simultaneously generating motion plans in a receding horizon fashion to control the pose of a grasped object. This approach consists of a discrete pose estimator that tracks the most likely sequence of object poses in a coarsely discretized grid, and a continuous pose estimator-controller to refine the pose estimate and accurately manipulate the pose of the grasped object. Our method is tested on diverse objects and configurations, achieving desired manipulation objectives and outperforming single-shot methods in estimation accuracy. The proposed approach holds potential for tasks requiring precise manipulation and limited intrinsic in-hand dexterity under visual occlusion, laying the foundation for closed-loop behavior in applications such as regrasping, insertion, and tool use. Please see this url for videos of real-world demonstrations.

Teleoperating robotic arms can be a challenging task for non-experts, particularly when using complex control devices or interfaces. To address the limitations and challenges of existing teleoperation frameworks, such as cognitive strain, control complexity, robot compatibility, and user evaluation, we propose TELESIM, a modular and plug-and-play framework that enables direct teleoperation of any robotic arm using a digital twin as the interface between users and the robotic system. Due to TELESIM’s modular design, it is possible to control the digital twin using any device that outputs a 3D pose, such as a virtual reality controller or a finger-mapping hardware controller. To evaluate the efficacy and user-friendliness of TELESIM, we conducted a user study with 37 participants. The study involved a simple pick-and-place task, which was performed using two different robots equipped with two different control modalities. Our experimental results show that most users were able to succeed by building at least a tower of 3 cubes in 10 minutes, with only 5 minutes of training beforehand, regardless of the control modality or robot used, demonstrating the usability and user-friendliness of TELESIM.

Social navigation and pedestrian behavior research has shifted towards machine learning-based methods and converged on the topic of modeling inter-pedestrian interactions and pedestrian-robot interactions. For this, large-scale datasets that contain rich information are needed. We describe a portable data collection system, coupled with a semi-autonomous labeling pipeline. As part of the pipeline, we designed a label correction web application that facilitates human verification of automated pedestrian tracking outcomes. Our system enables large-scale data collection in diverse environments and fast trajectory label production. Compared with existing pedestrian data collection methods, our system contains three components: a combination of top-down and ego-centric views, natural human behavior in the presence of a socially appropriate "robot", and human-verified labels grounded in the metric space. To the best of our knowledge, no prior data collection system has a combination of all three components. We further introduce our ever-expanding dataset from the ongoing data collection effort – the TBD Pedestrian Dataset and show that our collected data is larger in scale, contains richer information when compared to prior datasets with human-verified labels, and supports new research opportunities.

Space manipulator system (SMS) maneuvers can excite flexible appendages, while fuel sloshing effects impact its dynamics and performance. To predict this behavior and control such systems, sloshing and flexible appendages are modeled. A novel system identification scheme is developed, which identifies all parameters required for the reconstruction of system dynamics despite unmeasurable sloshing and modal states. This is achieved by two identification experiments. In Exp.1 all unmeasurable states are eliminated, while in Exp.2 the unmeasurable sloshing states are eliminated, and a novel estimator is used for the unmeasurable modal states. The significance of accurate SYSID in controller design and performance is demonstrated by simulating a 3D SMS controlled by model-based and robust controllers. In both cases, using the identified parameters results in significant robust control performance enhancement.

The creation of precise and high-resolution crop point clouds in agricultural fields has become a key challenge for high-throughput phenotyping applications. This work implements a novel calibration method to calibrate the laser scanning system of an agricultural field robot consisting of two industrial-grade laser scanners used for high-precise 3D crop point cloud creation. The calibration method optimizes the transformation between the scanner origins and the robot pose by minimizing 3D point omnivariances within the point cloud. Moreover, we present a novel factor graph-based pose estimation method that fuses total station prism measurements with IMU and GNSS heading information for high-precise pose determination during calibration. The root-mean-square error of the distances to a georeferenced ground truth point cloud results in 0.8 cm after parameter optimization. Furthermore, our results show the importance of a reference point cloud in the calibration method needed to estimate the vertical translation of the calibration. Challenges arise due to non-static parameters while the robot moves, indicated by systematic deviations to a ground truth terrestrial laser scan.

Successfully achieving bipedal locomotion remains challenging due to real-world factors such as model uncertainty, random disturbances, and imperfect state estimation. In this work, we propose a novel metric for locomotive robustness – the estimated size of the hybrid forward invariant set associated with the step-to-step dynamics. Here, the forward invariant set can be loosely interpreted as the region of attraction for the discrete-time dynamics. We illustrate the use of this metric towards synthesizing nominal walking gaits using a simulation-in-the-loop learning approach. Further, we leverage discrete-time barrier functions and a sampling-based approach to approximate sets that are maximally forward invariant. Lastly, we experimentally demonstrate that this approach results in successful locomotion for both flat-foot walking and multi-contact walking on the Atalante lower-body exoskeleton.

Safety certificates based on energy functions can provide demonstrable safety for complex robotic systems. However, all recent studies on learning-based energy function synthesis only consider the feasibility of the control policy, which might cause over-conservativeness and even fail to achieve the control goal. To solve the problem of over-conservative controllers, we proposed the magnitude regularization technique to improve the controller performance of safe controllers by reducing the conservativeness inside the energy function, while keeping the promising provable safety guarantees. Specifically, we quantify the conservativeness by the magnitude of the energy function, and we reduce the conservativeness by adding a magnitude regularization term to the synthesis loss. We propose an algorithm using reinforcement learning (RL) for synthesis to unify the learning process of safe controllers and energy functions. We conducted simulation experiments on Safety Gym and real-robot experiments using small quadrotors. Simulation results show that the proposed algorithm does reduce the conservativeness of the energy function and outperforms baselines in terms of controller performance while maintaining safety. Real-robot experiments have shown that the proposed algorithm indeed reduce conservativeness on the small quadrotors.

This paper investigates the problem of designing control policies that satisfy high-level specifications described by signal temporal logic (STL) in unknown, stochastic environments. While many existing works concentrate on optimizing the spatial robustness of a system, our work takes a step further by also considering temporal robustness as a critical metric to quantify the tolerance of time uncertainty in STL. To this end, we formulate two relevant control objectives to enhance the temporal robustness of the synthesized policies. The first objective is to maximize the probability of being temporally robust for a given threshold. The second objective is to maximize the worst-case spatial robustness value within a bounded time shift. We use reinforcement learning to solve both control synthesis problems for unknown systems. Specifically, we approximate both control objectives in a way that enables us to apply the standard Q-learning algorithm. Theoretical bounds in terms of the approximations are also derived. We present case studies to demonstrate the feasibility of our approach.

Synthetic data generation is a proven method for augmenting training sets without the need for extensive setups, yet its application in human activity recognition is underexplored. This is particularly crucial for human-robot collaboration in household settings, where data collection is often privacy-sensitive. In this paper, we introduce SynthAct, a synthetic data generation pipeline designed to significantly minimize the reliance on real-world data. Leveraging modern 3D pose estimation techniques, SynthAct can be applied to arbitrary 2D or 3D video action recordings, making it applicable for uncontrolled in-the-field recordings by robotic agents or smarthome monitoring systems. We present two SynthAct datasets: AMARV, a large synthetic collection with over 800k multi-view action clips, and Synthetic Smarthome, mirroring the Toyota Smarthome dataset. SynthAct generates a rich set of data, including RGB videos and depth maps from four synchronized views, 3D body poses, normal maps, segmentation masks and bounding boxes. We validate the efficacy of our datasets through extensive synthetic-to-real experiments on NTU RGB+D and Toyota Smarthome. SynthAct is available on our project page4.

We present and discuss the Synset Boulevard dataset, designed for the task of surveillance-nature vehicle make and model recognition (VMMR)—to the best of our knowledge the first entirely synthetically generated large-scale VMMR image dataset. Through the simulation of image data rather than the manual annotation of real data, we intend to mitigate common challenges in state-of-the-art VMMR datasets, namely bias, human error, privacy, and the challenge of providing systematic updates. On the other hand, the provision and use of synthetic data introduce individual challenges, such as potential domain gaps and a less pronounced intra-class variance. Our approach to address these challenges, using path tracing and physically-based, data-driven models, is evaluated on an existing large real-world dataset. Overall, our synthetic dataset contains 32 400 independent images (each with different imaging simulations and with/without masked license plates, leading to a total of 259 200 images) from 162 different vehicle models of 43 makes depicted in front view. It is split into 8 sub-datasets to investigate the influence of optical/imaging effects on the classification ability.

Synchronized dual-arm rearrangement is widely studied as a common scenario in industrial applications. It often faces scalability challenges due to the computational complexity of robotic arm rearrangement and the high-dimensional nature of dual-arm planning. To address these challenges, we formulated the problem as cooperative mTSP, a variant of mTSP where agents share cooperative costs, and utilized reinforcement learning for its solution. Our approach involved representing rearrangement tasks using a task state graph that captured spatial relationships and a cooperative cost matrix that provided details about action costs. Taking these representations as observations, we designed an attention-based network to effectively combine them and provide rational task scheduling. Furthermore, a cost predictor is also introduced to directly evaluate actions during both training and planning, significantly expediting the planning process. Our experimental results demonstrate that our approach outperforms existing methods in terms of both performance and planning efficiency.

Vision-based human-to-robot handover is an important and challenging task in human-robot interaction. Recent work has attempted to train robot policies by interacting with dynamic virtual humans in simulated environments, where the policies can later be transferred to the real world. However, a major bottleneck is the reliance on human motion capture data, which is expensive to acquire and difficult to scale to arbitrary objects and human grasping motions. In this paper, we introduce a framework that can generate plausible human grasping motions suitable for training the robot. To achieve this, we propose a hand-object synthesis method that is designed to generate handover-friendly motions similar to humans. This allows us to generate synthetic training and testing data with 100x more objects than previous work. In our experiments, we show that our method trained purely with synthetic data is competitive with state-of-the-art methods that rely on real human motion data both in simulation and on a real system. In addition, we can perform evaluations on a larger scale compared to prior work. With our newly introduced test set, we show that our model can better scale to a large variety of unseen objects and human motions compared to the baselines.

This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. Moreover, previous works do not incorporate potential domain symmetry and thus must search for solutions in a bigger space. Instead, we propose to leverage the symmetry for sample efficiency by augmenting the training data and constructing auxiliary losses to force the agent to adhere to the symmetry. Results in simulation with five different symmetric peg shapes show that our proposed agent can be comparable to or even outperform a state-based agent. In particular, the sample efficiency also allows us to learn directly on the real robot within 3 hours.

Symmetry is a fundamental aspect of many real-world robotic tasks. However, current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively. Often, the learned behaviors fail to achieve the desired transformation invariances and suffer from motion artifacts. For instance, a quadruped may exhibit different gaits when commanded to move forward or backward, even though it is symmetrical about its torso. This issue becomes further pronounced in high-dimensional or complex environments, where DRL methods are prone to local optima and fail to explore regions of the state space equally. Past methods on encouraging symmetry for robotic tasks have studied this topic mainly in a single-task setting, where symmetry usually refers to symmetry in the motion, such as the gait patterns. In this paper, we revisit this topic for goal-conditioned tasks in robotics, where symmetry lies mainly in task execution and not necessarily in the learned motions themselves. In particular, we investigate two approaches to incorporate symmetry invariance into DRL -– data augmentation and mirror loss function. We provide a theoretical foundation for using augmented samples in an on-policy setting. Based on this, we show that the corresponding approach achieves faster convergence and improves the learned behaviors in various challenging robotic tasks, from climbing boxes with a quadruped to dexterous manipulation.

There has been a growing interest in parallel strategies for solving trajectory optimization problems. One key step in many algorithmic approaches to trajectory optimization is the solution of moderately-large and sparse linear systems. Iterative methods are particularly well-suited for parallel solves of such systems. However, fast and stable convergence of iterative methods is reliant on the application of a high-quality preconditioner that reduces the spread and increase the clustering of the eigenvalues of the target matrix. To improve the performance of these approaches, we present a new parallel-friendly symmetric stair preconditioner. We prove that our preconditioner has advantageous theoretical properties when used in conjunction with iterative methods for trajectory optimization such as a more clustered eigenvalue spectrum. Numerical experiments with typical trajectory optimization problems reveal that as compared to the best alternative parallel preconditioner from the literature, our symmetric stair preconditioner provides up to a 34% reduction in condition number and up to a 25% reduction in the number of resulting linear system solver iterations.

While it is generally acknowledged that force feedback is beneficial to robotic control, applications of policy learning to robotic manipulation typically only leverage visual feedback. Recently, symmetric neural models have been used to significantly improve the sample efficiency and performance of policy learning across a variety of robotic manipulation domains. This paper explores an application of symmetric policy learning to visual-force problems. We present Symmetric Visual Force Learning (SVFL), a novel method for robotic control which leverages visual and force feedback. We demonstrate that SVFL can significantly outperform state of the art baselines for visual force learning and report several interesting empirical findings related to the utility of learning force feedback control policies in both general manipulation tasks and scenarios with low visual acuity.

Recent advances in robot-assisted surgery have resulted in progressively more precise, efficient, and minimally invasive procedures, sparking a new era of robotic surgical intervention. This enables doctors, in collaborative interaction with robots, to perform traditional or minimally invasive surgeries with improved outcomes through smaller incisions. Recent efforts are working toward making robotic surgery more autonomous which has the potential to reduce variability of surgical outcomes and reduce complication rates. Deep reinforcement learning methodologies offer scalable solutions for surgical automation, but their effectiveness relies on extensive data acquisition due to the absence of prior knowledge in successfully accomplishing tasks. Due to the intensive nature of simulated data collection, previous works have focused on making existing algorithms more efficient. In this work, we focus on making the simulator more efficient, making training data much more accessible than previously possible. We introduce Surgical Gym, an open-source high performance platform for surgical robot learning where both the physics simulation and reinforcement learning occur directly on the GPU. We demonstrate between 100-5000× faster training times compared with previous surgical learning platforms. The code is available at: https://github.com/SamuelSchmidgall/SurgicalGym.

This paper proposes the utilization of Supernumerary Robotic Limbs (SuperLimbs) for augmenting astronauts during an Extra-Vehicular Activity (EVA) in a partial-gravity environment. We investigate the effectiveness of SuperLimbs in assisting astronauts to their feet following a fall. Based on preliminary observations from a pilot human study, we categorized post-fall recoveries into a sequence of statically stable poses called "waypoints". The paths between the waypoints can be modeled with a simplified kinetic motion applied about a specific point on the body. Following the characterization of post-fall recoveries, we designed a task-space impedance control with high damping and low stiffness, where the SuperLimbs provide an astronaut with assistance in post-fall recovery while keeping the human-in-the-loop scheme. In order to validate this control scheme, a full-scale wearable analog space suit was constructed and tested with a SuperLimbs prototype. Results from the experimentation found that without assistance, astronauts would impulsively exert themselves to perform a post-fall recovery, which resulted in high energy consumption and instabilities maintaining an upright posture, concurring with prior NASA studies. When the SuperLimbs provided assistance, the astronaut’s energy consumption and deviation in their tracking as they performed a post-fall recovery was reduced considerably.