IROS 2023 Papers

Soft robots possess unique capabilities for adapting to the environment and interacting with it safely. However, their deformable nature also poses challenges for controlling their movement. In particular, the large deformations of a soft robot make it difficult to localize its individual body parts, which in turn impedes effective control. This paper introduces a novel localization framework designed for soft robots that are constrained by boundaries and benefit from unique hardware architecture. To this end, we propose a method that exploits the flexible boundaries of the robot to create an onboard sensor capable of measuring the relative distances between its sub-robots. This measurement data is incorporated into a linear Kalman filter for accurate localization. We evaluate the framework's performance in benchmark and dynamic cases and demonstrate its effectiveness in improving localization accuracy compared to an IMU-based approach. The results also show that the proposed method achieves sufficient localization accuracy for contact-based mapping, enabling the robot to sense the location of obstacles in the environment. Finally, we validate the proposed framework using a physical prototype of a boundary-constrained soft robot and demonstrate its ability to accurately estimate the robot's shape. This framework has the potential to enable soft robots to autonomously navigate and map unknown environments, which could be beneficial for a variety of exploration tasks.

This paper proposes a sustainable planning system for small-sized unmanned aerial vehicles (UAVs). Our mapping module of the system uses a voxel array as data structure with an introduced feature which is local map origin update. This approach has clear advantages that the planning system can sustainably plan trajectories regardless of operating radius and flight distance, and it shows fastest invariant time complexity \mathcal{O}(1)\mathcal{O}(1) unlike other representation methods. Also, we propose an efficient configuration space (C-space) construction algorithm using incremental voxel inflation, and extend state-of-the-art Euclidean signed distance field (ESDF) algorithm, FIESTA by applying the local map origin update feature. The proposed planning system requires single depth camera only as a sensor, and can operate in realtime on embedded computing platforms. We have verified the planning system through real-world flight tests in dense environments using a lightweight quadrotor plat-form under 300 mm size equipped with low-cost components only.

We present a hybrid-state path planner for autonomous surface vehicles (ASVs) constrained by a min-imum turning radius. The work is motivated by the future Norwegian naval mine countermeasures (NMCM) concept, which includes mine sweeping operations with ASVs that operate alone or in a formation of two, with and without mine sweeping equipment attached. Our path-planning approach is a variant of hybrid A* search, with the goal of finding the shortest path for transit in an environment consisting of an a priori map, operator-defined avoid areas and static obstacles detected by the vehicle. The planner is capable of finding traversable paths for ASV formations and single vehicles using a simple geometric model based on an estimated minimum turning radius for a given configuration. The method is modular as it is uncoupled from the path-following control method, making it applicable to many different systems, including our ASV configurations for mine sweeping operations. We present results from path planning in simulation for a single vehicle and two vehicles in formation. The method has been validated through a full-scale experiment with one of our ASVs in our testing area for autonomous platforms.

The trunk movements of an individual paralyzed by spinal cord injury (SCI) can be restored by Functional Neuromuscular Stimulation (FNS), a technique that applies low-level current to motor nerves to activate the muscles generating torques, and thus, produce trunk motions. FNS can be modulated to control trunk movements. However, a stabilizing modulation policy (i.e., control law) is difficult to derive due to the complexity of neuromusculoskeletal dynamics, which consist of skeletal dynamics (i.e., multi-joint rigid body dynamics) and neuromuscular dynamics (i.e., a highly nonlinear, non-autonomous, and input redundant dynamics). Therefore, an FNS-based control method that can stabilize the trunk without knowing the accurate skeletal and neuromuscular dynamics is desired. This work proposed an FNS generator, which consists of a robust nonlinear controller (RNC) that provides stabilizing torque command and an artificial neural network (ANN)-based torque-to-activation (T-A) map to ensure that the muscle generates the stabilizing torque to the skeleton. Due to the robustness and learning capability of this control framework, full knowledge of the trunk neuromusculoskeletal dynamics is not required. The proposed control framework has been tested in a simulation environment where an anatomically realistic 3D musculoskeletal model of the human trunk was manipulated to follow a time-varying reference that moves in the anterior-posterior and medial-lateral directions. From the results, it can be seen that the trunk motion converges to a satisfactory trajectory while the ANN is being updated. The results suggest the potential of this control framework for trunk tracking tasks in a clinical application.

Typical drones with multi rotors are generally less maneuverable due to unidirectional thrust, which may be unfavorable to agile flight in very narrow and confined spaces. This paper suggests a new bio-inspired drone that is empowered with high maneuverability in a lightweight and easy-to-carry way. The proposed flying squirrel inspired drone has controllable foldable wings to cover a wider range of flight attitudes and provide more maneuverable flight capability with stable tracking performance. The wings of a drone are fabricated with silicone membranes and sophisticatedly controlled by reinforcement learning based on human-demonstrated data. Specially, such learning based wing control serves to capture even the complex aerodynamics that are often impossible to model mathematically. It is shown through experiment that the proposed flying squirrel drone intentionally induces aerodynamic drag and hence provides the desired additional repulsive force even under saturated mechanical thrust. This work is very meaningful in demonstrating the potential of biomimicry and machine learning for realizing an animal-like agile drone.

Age-related loss of mobility and an increased risk of falling remain major obstacles for older adults to live independently. Many elderly people lack the coordination and strength necessary to perform activities of daily living, such as getting out of bed or stepping into a bathtub. A traditional solution is to install grab bars around the home. For assisting in bathtub transitions, grab bars are fixed to a bathroom wall. However, they are often too far to reach and stably support the user; the installation locations of grab bars are constrained by the room layout and are often suboptimal. In this paper, we present a mobile robot that provides an older adult with a handlebar located anywhere in space - “Handle Anywhere”. The robot consists of an omnidirectional mobile base attached to a reposition able handlebar. We further develop a methodology to optimally place the handle to provide the maximum support for the elderly user while performing common postural changes. A cost function with a trade-off between mechanical advantage and manipulability of the user's arm was optimized in terms of the location of the handlebar relative to the user. The methodology requires only a sagittal plane video of the elderly user performing the postural change, and thus is rapid, scalable, and uniquely customizable to each user. A proof-of-concept prototype was built, and the optimization algorithm for handle location was validated experimentally.

Multi-fingered robotic hands have potential to enable robots to perform sophisticated manipulation tasks. However, teaching a robot to grasp objects with an anthropomorphic hand is an arduous problem due to the high dimensionality of state and action spaces. Deep Reinforcement Learning (DRL) offers techniques to design control policies for this kind of problems without explicit environment or hand modeling. However, state-of-the-art model-free algorithms have proven inefficient for learning such policies. The main problem is that the exploration of the environment is unfeasible for such high-dimensional problems, thus hampering the initial phases of policy optimization. One possibility to address this is to rely on off-line task demonstrations, but, oftentimes, this is too demanding in terms of time and computational resources. To address these problems, we propose the A Grasp Pose is All You Need (G-PAYN) method for the anthropomorphic hand of the iCub humanoid. We develop an approach to automatically collect task demonstrations to initialize the training of the policy. The proposed grasping pipeline starts from a grasp pose generated by an external algorithm, used to initiate the movement. Then a control policy (previously trained with the proposed G-PAYN) is used to reach and grab the object. We deployed the iCub into the MuJoCo simulator and use it to test our approach with objects from the YCB-Video dataset. Results show that G-PAYN outperforms current DRL techniques in the considered setting in terms of success rate and execution time with respect to the baselines. The code to reproduce the experiments is released together with the paper with an open source license11https://github.com/hsp-iit/rl-icub-dexterous-manipulation.

Recent studies show that some security features that blockchains grant to decentralized networks on the internet can be ported to swarm robotics. Although the integration of blockchain technology and swarm robotics shows great promise, thus far, research has been limited to proof-of-concept scenarios where the blockchain-based mechanisms are tailored to a particular swarm task and operating environment. In this study, we propose a generic framework based on a blockchain smart contract that enables robot swarms to achieve secure consensus in an arbitrary observation space. This means that our framework can be customized to fit different swarm robotics missions, while providing methods to identify and neutralize Byzantine robots, that is, robots which exhibit detrimental behaviours stemming from faults or malicious tampering.

Planning safe robot motions in the presence of humans requires reliable forecasts of future human motion. However, simply predicting the most likely motion from prior interactions does not guarantee safety. Such forecasts fail to model the long tail of possible events, which are rarely observed in limited datasets. On the other hand, planning for worst-case motions leads to overtly conservative behavior and a “frozen robot”. Instead, we aim to learn forecasts that predict counterfactuals that humans guard against. We propose a novel game-theoretic framework for joint planning and forecasting with the payoff being the performance of the planner against the demonstrator, and present practical algorithms to train models in an end-to-end fashion. We demonstrate that our proposed algorithm results in safer plans in a crowd navigation simulator and real-world datasets of pedestrian motion. We release our code at https://github.com/portal-cornell/Game-Theoretic-Forecasting-Planning.

This paper proposes a modification of the Gaussian mixture probability hypothesis density (GM-PHD) filter to compute online the probability of detection (P_{D})(P_{D}) and probability of survival (P_{S})(P_{S}) of targets. This eliminates the need for predetermined and/or constant P_{D}P_{D} and P_{S}P_{S} values, that may degrade the estimation. The proposed filter estimates the P_{D}P_{D} and P_{S}P_{S} values for each individual target based on newly introduced parameters, which are updated during the measurement update process. The effectiveness of the proposed filter was validated through an in-lab experiment using four unmanned ground robots with varying P_{D}P_{D} values and a real-world lidar-based obstacle tracking system implemented on an Automated Surface Vehicle operating in a lake with real-time boat traffic. The results of the experiments demonstrate that the proposed filter outperforms the standard PHD filter with incorrect P_{D}P_{D} and P_{S}P_{S} values. These findings highlight the potential benefits of the proposed filter in improving target tracking performance in complex environments.

Despite recent progress in Reinforcement Learning for robotics applications, many tasks remain prohibitively difficult to solve because of the expensive interaction cost. Transfer learning helps reduce the training time in the target domain by transferring knowledge learned in a source domain. Sim2Real transfer helps transfer knowledge from a simulated robotic domain to a physical target domain. Knowledge transfer reduces the time required to train a task in the physical world, where the cost of interactions is high. However, most existing approaches assume exact correspondence in the task structure and the physical properties of the two domains. This work proposes a framework for Few-Shot Policy Transfer between two domains through Observation Mapping and Behavior Cloning. We use Generative Adversarial Networks (GANs) along with a cycle-consistency loss to map the observations between the source and target domains and later use this learned mapping to clone the successful source task behavior policy to the target domain. We observe successful behavior policy transfer with limited target task interactions and in cases where the source and target task are semantically dissimilar.

This paper presents the modeling and closed loop control of the shape-memory-alloy (SMA)-actuated hip joint of a flapping-wing flying robot (FWFR). Despite the lightweight legs/claw mechanism, a strong force of grasping is needed. The SMAs show high force delivery; however, it is difficult to control (position and temperature) the actuation due to the necessity of high currents for warming up, and time for cooling down process. This paper presents a state-dependent differential Riccati equation (SDDRE) controller taking into account the SMA dynamic and the actuator limits to control the leg/claw system. The use of nonlinear optimal control, specifically, the SDDRE, has been reported for the first time for bio-inspired leg/claw control of FWFR. The dynamics of the SMA actuators and on-off switching of the MOSFETs to provide current for the system demands switching in the design of the controller as a constraint for inputs which was considered in the design. Simulation and experimental results and analysis of different phases of heating of SMAs were discussed and resulted in satisfactory control performance.

To handle the two shortcomings of existing methods, (i) nearly all models rely on high-definition (HD) maps, yet the map information is not always available in real traffic scenes and HD map-building is expensive and time-consuming and (ii) existing models usually focus on improving prediction accuracy at the expense of reducing computing efficiency, yet the efficiency is crucial for various real applications, this paper proposes an efficient trajectory prediction model that is not dependent on traffic maps. The core idea of our model is encoding single-agent's spatial-temporal information in the first stage and exploring multi-agents' spatial-temporal interactions in the second stage. By comprehensively utilizing attention mechanism, LSTM, graph convolution network and temporal transformer in the two stages, our model is able to learn rich dynamic and interaction information of all agents. Our model achieves the highest performance when comparing with existing map-free methods and also exceeds most map-based state-of-the-art methods on the Argoverse dataset. In addition, our model also exhibits a faster inference speed than the baseline methods.

Soft vibrational bristlebots are robots with deformable bristles on their outside that propel the robot through the stick slip motion of the bristle tips interacting with the ground when a vibration is induced in the robot. Experimental results and theoretical analysis of the dynamics for this style of robot have been investigated on flat surfaces. However, for the soft vibrational bristlebots traveling through pipes, controlled steering and the ability for the robot to navigate intersections has not been achieved or understood. This paper presents a two unit vibrational bristlebot with connecting helical coils. Through models and experiments it is demonstrated that a full range of controlled motion (traveling forwards, turning left and right and going up or down a vertical pipe) within a pipe network is possible for such soft vibrational bristlebots. Such fast steerable motion is all achieved merely by changing the polarity and spin speed of the vibrational motors.

We explore the idea of robotic mechanisms that can shift between soft and rigid states, with the long-term goal of creating robots that marry the flexibility and robustness of soft robots with the strength and precision of rigid robots. We present a simple yet effective method to achieve large and rapid stiffness variations by compressing and relaxing a flexure using cables. Next, we provide a differentiable modeling framework that can be used for motion planning, which simultaneously reasons about the modulated stiffness joints, tendons, rigid joints, and basic hydrodynamics. We apply this stiffness tuning and simulation recipe to create SoRiTu, an untethered soft-rigid robotic sea turtle capable of various swimming maneuvers.

A common operation in multirobot systems is to generate a motion plan for multiple robots such that the robots can move in formation to achieve some desired effects. For example, in autonomous parking lots, a group of vehicles can be asked to move to another location when they block another vehicle that needs to leave the parking lot. In this paper, we present a novel grid-based planning approach for motion planning that minimizes the makespan of moving multiple vehicles from one location to another in a safe manner. Unlike most existing multirobot planning algorithms, our algorithm uses dynamic programming to compute a nearly-optimal motion plan for a large group of vehicles in polynomial time with the help of a given set of intermediate vehicle patterns. Our experimental results show that our algorithm is much faster than an exact algorithm but does not increase the minimum makespans tremendously.

UAV swarms have attracted much attention for post-disaster search and rescue, pollution monitoring and trace-ability, etc., where distributed scheduling is required to arrange careful tasks and time quickly. The market-based methods are widely favored but they rely on the environmentally influenced communication network to complete negotiation, while the on-board computing of UAV is robust and redundant. This paper proposes a distributed scheduling method for networked UAV swarm based on computing for communication, which trades a modest increase in computing for a significant decrease in communication. First, by analyzing the task removal strategies of two representative methods, the consensus-based bundle algorithm (CBBA) and performance impact (PI) algorithm, a new removal strategy is proposed, which expands the explo-ration of the bundle and can potentially reduce communication rounds. Second, the proposed task-related optimization method can extract task conflict nodes from the native communication protocol, and use the sampling and estimation strategies to resolve task conflicts in advance. Third, historical bids are cleverly used to infer others' locations, which is necessary for task-related optimization. Fourth, to verify the algorithm in real communication, a hardware-in-the-loop (HIL) ad-hoc network simulation system is constructed, which uses real network protocols and simulated channel transmissions. Finally, the HIL Monte Carlo simulation results show that, compared with CBBA and PI, the proposed method can significantly reduce the number of communication rounds and the total scheduling time, without increasing the communication protocol overhead and loss of optimization.

Autonomous mobile robots (AMR) operating in the real world often need to make critical decisions that directly impact their own safety and the safety of their surroundings. Learning-based approaches for decision making have gained popularity in recent years, since decisions can be made very quickly and with reasonable levels of accuracy for many applications. These approaches, however, typically return only one decision, and if the learner is poorly trained or observations are noisy, the decision may be incorrect. This problem is further exacerbated when the robot is making decisions about its own failures, such as faulty actuators or sensors and external disturbances, when a wrong decision can immediately cause damage to the robot. In this paper, we consider this very case study: a robot dealing with such failures must quickly assess uncertainties and make safe decisions. We propose an uncertainty aware learning-based failure detection and recovery approach, in which we leverage Decision Tree theory along with Model Predictive Control to detect and explain which failure is compromising the system, assess uncertainties associated with the failure, and lastly, find and validate corrective controls to recover the system. Our approach is validated with simulations and real experiments on a faulty unmanned ground vehicle (UGV) navigation case study, demonstrating recovery to safety under uncertainties.