ICRA 2024 Papers

Coordinated landing control for multiple unmanned aerial vehicles (UAVs) on appropriate multiple unmanned surface vehicles (USVs) is an urgent yet challenging mission with the tremendous development of modern marine industry. To this end, we propose a coordinated multiple UAV-USV landing control algorithm via heterogeneous-feature matching. Specifically, the heterogeneous landing features of different UAVs and USVs are extracted to establish a dynamic UAV-USV cooperative landing ability mapping for the cross-domain UAV-USV fleets (CDUUFs). Then, by incorporating suitable allocation with UAV-USV landing convergence and collision avoidance among UAVs into constraints with the assistance of both control Lyapunov functions (CLFs) and control barrier functions (CBFs), the multiple UAV-USV landing control problem is formulated as a constraint-based optimization one. Therein, slack variables are introduced to fulfill the assignment and facilitate the searching of a balanced solution between control performance and landing safety. Finally, extensive simulations are conducted to substantiate the effectiveness of the present multiple UAV-USV landing control law.

A surgeon’s physiological hand tremor can significantly impact the outcome of delicate and precise retinal surgery, such as retinal vein cannulation (RVC) and epiretinal membrane peeling. Robot-assisted eye surgery technology provides ophthalmologists with advanced capabilities such as hand tremor cancellation, hand motion scaling, and safety constraints that enable them to perform these otherwise challenging and high-risk surgeries with high precision and safety. Steady-Hand Eye Robot (SHER) with cooperative control mode can filter out surgeon’s hand tremor, yet another important safety feature, that is, minimizing the contact force between the surgical instrument and sclera surface for avoiding tissue damage cannot be met in this control mode. Also, other capabilities, such as hand motion scaling and haptic feedback, require a teleoperation control framework. In this work, for the first time, we implemented a teleoperation control mode incorporated with an adaptive sclera force control algorithm using a PHANTOM Omni haptic device and a force-sensing surgical instrument equipped with Fiber Bragg Grating (FBG) sensors attached to the SHER 2.1 end-effector. This adaptive sclera force control algorithm allows the robot to dynamically minimize the toolsclera contact force. Moreover, for the first time, we compared the performance of the proposed adaptive teleoperation mode with the cooperative mode by conducting a vessel-following experiment inside an eye phantom under a microscope.

Cooking recipes are challenging to translate to robot plans as they feature rich linguistic complexity, temporally-extended interconnected tasks, and an almost infinite space of possible actions. Our key insight is that combining a source of cooking domain knowledge with a formalism that captures the temporal richness of cooking recipes could enable the extraction of unambiguous, robot-executable plans. In this work, we use Linear Temporal Logic (LTL) as a formal language expressive enough to model the temporal nature of cooking recipes. Leveraging a pretrained Large Language Model (LLM), we present Cook2LTL, a system that translates instruction steps from an arbitrary cooking recipe found on the internet to a set of LTL formulae, grounding high-level cooking actions to a set of primitive actions that are executable by a manipulator in a kitchen environment. Cook2LTL makes use of a caching scheme that dynamically builds a queryable action library at runtime. We instantiate Cook2LTL in a realistic simulation environment (AI2-THOR), and evaluate its performance across a series of cooking recipes. We demonstrate that our system significantly decreases LLM API calls (−51%), latency (−59%), and cost (−42%) compared to a baseline that queries the LLM for every newly encountered action at runtime.

A novel deep neural network (DNN) based controller for omnidirectional robots is proposed. The controller decomposes the prescribed reference path, corresponding to a fixed prediction horizon, into multiple paths of shorter horizons. This implicitly enforces a Hankel structure in the input and consequently also on the output. Taking advantage of this, a convolutional vision transformer model is used to realize the controller which is then trained to predict state and controls over multiple prediction horizons. Model training is performed in a self-supervised manner using a synthetic dataset. The proposed controller is shown to be more efficient than a model designed for a single prediction horizon. In comparison to a model predictive controller, the proposed approach exhibits competitive performance in path following tasks and is three times faster on average for the same prediction length.

In order to perform highly dynamic and agile maneuvers, legged robots typically spend time in underactuated domains (e.g. with feet off the ground) where the system has limited command of its acceleration and a constrained amount of time before transitioning to a new domain (e.g. foot touchdown). Meanwhile, these transitions can instantaneously change the system’s state, possibly causing perturbations to be mapped arbitrarily far away from the target trajectory. These properties make it difficult for local feedback controllers to effectively recover from disturbances as the system evolves through underactuated domains and hybrid impact events. To address this, we utilize the fundamental solution matrix that characterizes the evolution of perturbations through a hybrid trajectory and its 2-norm, which represents the worst-case growth of perturbations. In this paper, the worst-case perturbation analysis is used to explicitly reason about the tracking performance of a hybrid trajectory and is incorporated in an iLQR framework to optimize a trajectory while taking into account the closed-loop convergence of the trajectory under an LQR tracking controller. The generated convergent trajectories recover more effectively from perturbations, are more robust to large disturbances, and use less feedback control effort than trajectories generated with traditional methods.

Upper limb paralysis affects the quality of life. Functional Electrical Stimulation (FES) offers a solution to restore lost motor functions. Yet, there remain challenges in controlling FES to induce arbitrary arm movements. Reinforcement learning (RL) emerges as a promising method for controlling arm movement with success in simulation. However, challenges remain in translating the successes into real-world settings. One dominant challenge is the sample efficiency of RL. This study presents a practical RL setup to control FES for arm movements. We also present a flexible method, called co-kriging adjustment (CKA), which combines a biomechanical simulator and real data to build an accurate model of the real system. We demonstrate our RL-based control on a 2-DoF planar setting where the subject’s arm, placed on a frictionless supporter, is stimulated to perform point-to-point reaching. By using 90 seconds of real interaction data, our RL-based control can perform the reaching with the average error over the workspace of 5.5 cm. Beyond the application of FES, our method can be extended to other control systems, propelling RL towards general uses in the real world.

In this paper, we consider a Micro Aerial Vehicle (MAV) system teleoperated by a non-expert and introduce a perceptive safety filter that leverages Control Barrier Functions (CBFs) in conjunction with Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) and dense 3D occupancy mapping to guarantee safe navigation in complex and unstructured environments. Our system relies solely on onboard IMU measurements, stereo infrared images, and depth images and autonomously corrects teleoperated inputs when they are deemed unsafe. We define a point in 3D space as unsafe if it satisfies either of two conditions: (i) it is occupied by an obstacle, or (ii) it remains unmapped. At each time step, an occupancy map of the environment is updated by the VI-SLAM by fusing the onboard measurements, and a CBF is constructed to parameterize the (un)safe region in the 3D space. Given the CBF and state feedback from the VI-SLAM module, a safety filter computes a certified reference that best matches the teleoperation input while satisfying the safety constraint encoded by the CBF. In contrast to existing perception-based safe control frameworks, we directly close the perception-action loop and demonstrate the full capability of safe control in combination with real-time VI-SLAM without any external infrastructure or prior knowledge of the environment. We verify the efficacy of the perceptive safety filter in real-time MAV experiments using exclusively onboard sensing and computation and show that the teleoperated MAV is able to safely navigate through unknown environments despite arbitrary inputs sent by the teleoperator.

The outdoor environment has many uneven surfaces that put the robot at risk of sinking or tipping over. Recognizing the type of terrain can help robot avoid risks and choose an appropriate gait. One of the critical problems is how to extract the terrain-related knowledge from sensor data collected as the robot traversed the ground. Many existing vision-based approaches are limited in directly perceiving the intrinsic properties of various terrains. The intuitive approach entails directly analyzing data recorded by the robot’s proprioceptive sensors. However, it faces challenges in being specific to certain robot leg configurations or in the lack of interpretability of the extracted features. In this paper, a terrain attribute extraction algorithm is proposed based on contrastive learning. It leverages the haptic data generated from the interaction between the robot’s legs and terrain to automatically extract terrain attributes. The results demonstrate that the attributes extracted using this method strongly correlate with the actual softness of the terrain. Furthermore, these attributes played an important role in achieving high accuracy in terrain classification tasks.

Scene transfer for vision-based mobile robotics applications is a highly relevant and challenging problem. The utility of a robot greatly depends on its ability to perform a task in the real world, outside of a well-controlled lab environment. Existing scene transfer end-to-end policy learning approaches often suffer from poor sample efficiency or limited generalization capabilities, making them unsuitable for mobile robotics applications. This work proposes an adaptive multi-pair contrastive learning strategy for visual representation learning that enables zero-shot scene transfer and real-world deployment. Control policies relying on the embedding are able to operate in unseen environments without the need for finetuning in the deployment environment. We demonstrate the performance of our approach on the task of agile, vision-based quadrotor flight. Extensive simulation and real-world experiments demonstrate that our approach successfully generalizes beyond the training domain and outperforms all baselines. Video: https://youtu.be/4A4YyPgEWD8

In Reinforcement Learning, the trade-off between exploration and exploitation poses a complex challenge for achieving efficient learning from limited samples. While recent works have been effective in leveraging past experiences for policy updates, they often overlook the potential of reusing past experiences for data collection. Independent of the underlying RL algorithm, we introduce the concept of a Contrastive Initial State Buffer, which strategically selects states from past experiences and uses them to initialize the agent in the environment in order to guide it toward more informative states. We validate our approach on two complex robotic tasks without relying on any prior information about the environment: (i) locomotion of a quadruped robot traversing challenging terrains and (ii) a quadcopter drone racing through a track. The experimental results show that our initial state buffer achieves higher task performance than the nominal baseline while also speeding up training convergence.

The emergence of intelligent prostheses has facilitated the life and work of disabled patients. The interaction aspect of prostheses has become a highlight research topic in the field of rehabilitation robotics. However, most of the existing prosthetic interaction methods focus on the use of myoelectricity to classify finite gestures, rather than continuous (infinite) force detection, which greatly limits the use of prosthetic scenarios. In this study, a novel optical waveguide sensor was used to collect muscle deformation information from the human arm for continuous control of the prosthetic grip force. The optical waveguide sensor was embedded with carbon fiber to limit the stretching of the waveguide, which led to the optical waveguide sensor being sensitive to bending deformation. Compared with EMGs, the accuracy of continuous grip force control based on the optical waveguide sensor is higher. The R-Square for prosthetic grip force and hand grip force were 0.867 and 0.9724 in the periodic and sustaining grip force experiments, respectively. The results suggested that the proposed method could provide a new approach to the interaction of prostheses.

Target tracking is a fundamental task in the domain of robotics. The effectiveness of target tracking hinges upon various factors, such as tracking distance, occlusions, collision avoidance, etc. However, few existing works can simultaneously tackle these considerations of tracking single and multiple targets in complex environments. In this study, the interaction mechanism of target tracking between the robot, the environment and the targets is analyzed, and a general measure named detectability is introduced to correlate the tracking performance for guiding robotic motion planning. Based on the detectability measure, the robotic motion planning framework based on Model Predictive Control (MPC) is proposed to achieve continuous and robust tracking of single, two and three targets in complex environments. Simulations and experiments are performed and verify the performances of our method better than the state-of-the-art methods.

In scenarios of Human-Robot Interaction (HRI), it is often assumed that the robot should cooperate with the closest individual or that only one person is present. However, in real-life situations, such as shop floor operations, this assumption may not hold. Thus, it becomes necessary for a robot to recognize a specific target in a crowded environment. To address this problem, we propose a person re-identification module that uses continuous visual adaptation techniques. This module ensures that the robot can seamlessly cooperate with the appropriate individual despite its appearance changes or partial or total occlusions. We used both a laboratory environment and an HRI scenario where the robot followed a person to test our framework. During the test, the targets were asked to change their appearance and disappear from the camera’s field of view to test the module’s ability to handle challenging cases of occlusion and outfit variations. We compared our framework with a state-of-the-art Multi-Object Tracking (MOT) method, and the results showed that our module, shortly named CARPE-ID, accurately tracked each selected target throughout the experiments in all cases except for two cases. In contrast, the MOT had an average of 4 tracking errors for each video.

The safety of autonomous vehicles (AV) has been a long-standing top concern, stemming from the absence of rare and safety-critical scenarios in the long-tail naturalistic driving distribution. To tackle this challenge, a surge of research in scenario-based autonomous driving has emerged, with a focus on generating high-risk driving scenarios and applying them to conduct safety-critical testing of AV models. However, limited work has been explored on the reuse of these extensive scenarios to iteratively improve AV models. Moreover, it remains intractable and challenging to filter through gigantic scenario libraries collected from other AV models with distinct behaviors, attempting to extract transferable information for current AV improvement. Therefore, we develop a continual driving policy optimization framework featuring Closed-Loop Individualized Curricula (CLIC), which we factorize into a set of standardized sub-modules for flexible implementation choices: AV Evaluation, Scenario Selection, and AV Training. CLIC frames AV Evaluation as a collision prediction task, where it estimates the chance of AV failures in these scenarios at each iteration. Subsequently, by re-sampling from historical scenarios based on these failure probabilities, CLIC tailors individualized curricula for downstream training, aligning them with the evaluated capability of AV. Accordingly, CLIC not only maximizes the utilization of the vast pre-collected scenario library for closed-loop driving policy optimization but also facilitates AV improvement by individualizing its training with more challenging cases out of those poorly organized scenarios. Experimental results clearly indicate that CLIC surpasses other curriculum-based training strategies, showing substantial improvement in managing risky scenarios, while still maintaining proficiency in handling simpler cases.

Containerized vertical farming is a type of vertical farming practice using hydroponics in which plants are grown in vertical layers within a mobile shipping container. Space limitations within shipping containers make the automation of different farming operations challenging. In this paper, we explore the use of cobots (i.e., collaborative robots) to automate two key farming operations, namely, the transplantation of saplings and the harvesting of grown plants. Our method uses a single demonstration from a farmer to extract the motion constraints associated with the tasks, namely, transplanting and harvesting, and can then generalize to different instances of the same task. For transplantation, the motion constraint arises during insertion of the sapling within the growing tube, whereas for harvesting, it arises during extraction from the growing tube. We present experimental results to show that using RGBD camera images (obtained from an eye-in-hand configuration) and one demonstration for each task, it is feasible to perform transplantation of saplings and harvesting of leafy greens using a cobot, without task-specific programming.

Multi-goal robot manipulation tasks with sparse rewards are difficult for reinforcement learning (RL) algorithms due to the inefficiency in collecting successful experiences. Recent algorithms such as Hindsight Experience Replay (HER) expedite learning by taking advantage of failed trajectories and replacing the desired goal with one of the achieved states so that any failed trajectory can be utilized as a contribution to learning. However, HER uniformly chooses failed trajectories, without taking into account which ones might be the most valuable for learning. In this paper, we address this problem and propose a novel approach Contact Energy Based Prioritization (CEBP) to select the samples from the replay buffer based on rich information due to contact, leveraging the touch sensors in the gripper of the robot and object displacement. Our prioritization scheme favors sampling of contact-rich experiences, which are arguably the ones providing the largest amount of information. We evaluate our proposed approach on various sparse reward robotic tasks and compare it with the state-of-the-art methods. We show that our method surpasses or performs on par with those methods on robot manipulation tasks. Finally, we deploy the trained policy from our method to a real Franka robot for a pick-and-place task. We observe that the robot can solve the task successfully. The videos and code are publicly available at: https://erdiphd.github.io/HER_force/.

Passivity is necessary for robots to fluidly collaborate and interact with humans physically. Nevertheless, due to the unconstrained nature of passivity-based impedance control laws, the robot is vulnerable to infeasible and unsafe configurations upon physical perturbations. In this paper, we propose a novel control architecture that allows a torque-controlled robot to guarantee safety constraints such as kinematic limits, self-collisions, external collisions and singularities and is passive only when feasible. This is achieved by constraining a dynamical system based impedance control law with a relaxed hierarchical control barrier function quadratic program subject to multiple concurrent, possibly contradicting, constraints. Joint space constraints are formulated from efficient data-driven self- and external {\mathcal{C}^2}{\mathcal{C}^2} collision boundary functions. We theoretically prove constraint satisfaction and show that the robot is passive when feasible. Our approach is validated in simulation and real robot experiments on a 7DoF Franka Research 3 manipulator.

Disturbance observer (DOB) is a well-known two-loop control structure that imparts robustness to a controller with a simple implementation. As a nonlinear DOB for the robotic systems, we proposed so-called nonlinear robust internal-loop compensator (NRIC) framework in our previous work. In this paper, we further extend the NRIC in such a way that an optimization scheme can be embedded in the control structure. The proposed method is called constrained NRIC (C-NRIC), because the optimization allows us to impose constraints, by which a controller acquires additional properties. As a particular use case of the C-NRIC framework, we design contact-responsive motion controllers that enables a robot to react to unknown interactions while accurately tracking the desired trajectory in free motion. The effectiveness of such designs is validated through the real-world experiments.

Optimal plans in Constrained Partially Observable Markov Decision Processes (CPOMDPs) maximize reward objectives while satisfying hard cost constraints, generalizing safe planning under state and transition uncertainty. Unfortunately, online CPOMDP planning is extremely difficult in large or continuous problem domains. In many large robotic domains, hierarchical decomposition can simplify planning by using tools for low-level control given high-level action primitives (options). We introduce Constrained Options Belief Tree Search (COBeTS) to leverage this hierarchy and scale online search-based CPOMDP planning to large robotic problems. We show that if primitive option controllers are defined to satisfy assigned constraint budgets, then COBeTS will satisfy constraints anytime. Otherwise, COBeTS will guide the search towards a safe sequence of option primitives, and hierarchical monitoring can be used to achieve runtime safety. We demonstrate COBeTS in several safety-critical, constrained partially observable robotic domains, showing that it can plan successfully in continuous CPOMDPs while non-hierarchical baselines cannot.