Search

Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance. Existing works on object removal erase removal targets using image inpainting networks. However, image inpainting networks often generate unsatisfactory removal results. In this work, we find that the current training approach which encourages a single image inpainting model to handle both object removal and restoration tasks is one of the reasons behind such unsatisfactory result. Based on this finding, we propose a task-decoupled image inpainting framework which generates two separate inpainting models: an object restorer for object restoration tasks and an object remover for object removal tasks. We train the object restorer with the masks that partially cover the removal targets. Then, the proposed framework makes an object restorer to generate a guidance for training the object remover. Using the proposed framework, we obtain a class-specific object remover which focuses on removing objects of a target class, aiming to better erase target class objects than general object removers. We also introduce a data curation method that encompasses the image selection and mask generation approaches used to produce training data for the proposed class-specific object remover. Using the proposed curation method, we can simulate the scenarios where an object remover is trained on the data with object removal ground truth images. Experiments on multiple datasets show that the proposed class-specific object remover can better remove target class objects than object removers based on image inpainting networks.

Constraint admissible positively invariant (CAPI) sets play a pivotal role in ensuring safety in control and planning applications, such as the recursive feasibility guarantee of explicit reference governor and model predictive control. However, existing methods for finding CAPI sets for nonlinear systems are often limited to single equilibria or specific system dynamics. This limitation underscores the necessity for a method to construct a CAPI set for general reference tracking control and a broader range of systems. In this work, we leverage recent advancements in learning-based methods to derive Lyapunov functions, particularly focusing on those with piecewise-affine activation functions. Previous attempts to find an invariant set with the piecewise-affine neural Lyapunov function have focused on the estimation of the region of attraction with mixed integer programs. We propose a methodology to determine the maximal CAPI set for any reference with the neural Lyapunov function by transforming the problem into multiple linear programs. Additionally, to enhance applicability in real-time control scenarios, we introduce a learning-based approach to train the estimator, which infers the CAPI set from a given reference. The proposed approach is validated with multiple simulations to show that it can generate a valid CAPI set with the given neural Lyapunov functions for any reference. We also employ the proposed CAPI set estimation method in the explicit reference governor and demonstrate its effectiveness for constrained control., Comment: 8 pages, 6 figures, Accepted to 63nd IEEE Conference on Decision and Control (CDC 2024)

This letter presents a versatile trajectory planning pipeline for aerial tracking. The proposed tracker is capable of handling various chasing settings such as complex unstructured environments, crowded dynamic obstacles and multiple-target following. Among the entire pipeline, we focus on developing a predictor for future target motion and a chasing trajectory planner. For rapid computation, we employ the sample-check-select strategy: modules sample a set of candidate movements, check multiple constraints, and then select the best trajectory. Also, we leverage the properties of Bernstein polynomials for quick calculations. The prediction module predicts the trajectories of the targets, which do not overlap with static and dynamic obstacles. Then the trajectory planner outputs a trajectory, ensuring various conditions such as occlusion and collision avoidance, the visibility of all targets within a camera image and dynamical limits. We fully test the proposed tracker in simulations and hardware experiments under challenging scenarios, including dual-target following, environments with dozens of dynamic obstacles and complex indoor and outdoor spaces., Comment: 8 pages, 9 figures

Neural implicit representation has attracted attention in 3D reconstruction through various success cases. For further applications such as scene understanding or editing, several works have shown progress towards object compositional reconstruction. Despite their superior performance in observed regions, their performance is still limited in reconstructing objects that are partially observed. To better treat this problem, we introduce category-level neural fields that learn meaningful common 3D information among objects belonging to the same category present in the scene. Our key idea is to subcategorize objects based on their observed shape for better training of the category-level model. Then we take advantage of the neural field to conduct the challenging task of registering partially observed objects by selecting and aligning against representative objects selected by ray-based uncertainty. Experiments on both simulation and real-world datasets demonstrate that our method improves the reconstruction of unobserved parts for several categories., Comment: RA-L. 8 pages, 8 figures, 4 tables

Bilateral teleoperation of an aerial manipulator facilitates the execution of industrial missions thanks to the combination of the aerial platform's maneuverability and the ability to conduct complex tasks with human supervision. Heretofore, research on such operations has focused on flying without any physical interaction or exerting a pushing force on a contact surface that does not involve abrupt changes in the interaction force. In this paper, we propose a human reaction time compensating haptic-based bilateral teleoperation strategy for an aerial manipulator extracting a wedged object from a static structure (i.e., plug-pulling), which incurs an abrupt decrease in the interaction force and causes additional difficulty for an aerial platform. A haptic device composed of a 4-degree-of-freedom robotic arm and a gripper is made for the teleoperation of aerial wedged object-extracting tasks, and a haptic-based teleoperation method to execute the aerial manipulator by the haptic device is introduced. We detect the extraction of the object by the estimation of the external force exerted on the aerial manipulator and generate reference trajectories for both the aerial manipulator and the haptic device after the extraction. As an example of the extraction of a wedged object, we conduct comparative plug-pulling experiments with a quadrotor-based aerial manipulator. The results validate that the proposed bilateral teleoperation method reduces the overshoot in the aerial manipulator's position and ensures fast recovery to its initial position after extracting the wedged object., Comment: to be presented in 2024 IEEE International Conference on Unmanned Aircraft Systems (ICUAS), Chania, Crete, Greece, 2024

This work proposes a saturated robust controller for a fully actuated multirotor that takes disturbance rejection and rotor thrust saturation into account. A disturbance rejection controller is required to prevent performance degradation in the presence of parametric uncertainty and external disturbance. Furthermore, rotor saturation should be properly addressed in a controller to avoid performance degradation or even instability due to a gap between the commanded input and the actual input during saturation. To address these issues, we present a modified saturated RISE (Robust Integral of the Sign of the Error) control method. The proposed modified saturated RISE controller is developed for expansion to a system with a non-diagonal, state-dependent input matrix. Next, we present reformulation of the system dynamics of a fully actuated multirotor, and apply the control law to the system. The proposed method is validated in simulation where the proposed controller outperforms the existing one thanks to the capability of handling the input matrix., Comment: 6 pages, 5 figures, 2024 International Conference on Unmanned Aircraft Systems (ICUAS) accepted

Aerial unperching of multirotors has received little attention as opposed to perching that has been investigated to elongate operation time. This study presents a new aerial robot capable of both perching and unperching autonomously on/from a ferromagnetic surface during flight, and a switching controller to avoid rotor saturation and mitigate overshoot during transition between free-flight and perching. To enable stable perching and unperching maneuvers on/from a vertical surface, a lightweight ($\approx$ $1$ \si{kg}), fully actuated tiltrotor that can hover at $90^\circ$ pitch angle is first developed. We design a perching/unperching module composed of a single servomotor and a magnet, which is then mounted on the tiltrotor. A switching controller including exclusive control modes for transitions between free-flight and perching is proposed. Lastly, we propose a simple yet effective strategy to ensure robust perching in the presence of measurement and control errors and avoid collisions with the perching site immediately after unperching. We validate the proposed framework in experiments where the tiltrotor successfully performs perching and unperching on/from a vertical surface during flight. We further show effectiveness of the proposed transition mode in the switching controller by ablation studies where large overshoot and even collision with a perching site occur. To the best of the authors' knowledge, this work presents the first autonomous aerial unperching framework using a fully actuated tiltrotor., Comment: 7 pages, 10 figures, 2024 IEEE International Conference on Robotics and Automation (ICRA) accepted

Object removal refers to the process of erasing designated objects from an image while preserving the overall appearance, and it is one area where image inpainting is widely used in real-world applications. The performance of an object remover is quantitatively evaluated by measuring the quality of object removal results, similar to how the performance of an image inpainter is gauged. Current works reporting quantitative performance evaluations utilize original images as references. In this letter, to validate the current evaluation methods cannot properly evaluate the performance of an object remover, we create a dataset with object removal ground truth and compare the evaluations made by the current methods using original images to those utilizing object removal ground truth images. The disparities between two evaluation sets validate that the current methods are not suitable for measuring the performance of an object remover. Additionally, we propose new evaluation methods tailored to gauge the performance of an object remover. The proposed methods evaluate the performance through class-wise object removal results and utilize images without the target class objects as a comparison set. We confirm that the proposed methods can make judgments consistent with human evaluators in the COCO dataset, and that they can produce measurements aligning with those using object removal ground truth in the self-acquired dataset.

Generative modeling of complex behaviors from labeled datasets has been a longstanding problem in decision making. Unlike language or image generation, decision making requires modeling actions - continuous-valued vectors that are multimodal in their distribution, potentially drawn from uncurated sources, where generation errors can compound in sequential prediction. A recent class of models called Behavior Transformers (BeT) addresses this by discretizing actions using k-means clustering to capture different modes. However, k-means struggles to scale for high-dimensional action spaces or long sequences, and lacks gradient information, and thus BeT suffers in modeling long-range actions. In this work, we present Vector-Quantized Behavior Transformer (VQ-BeT), a versatile model for behavior generation that handles multimodal action prediction, conditional generation, and partial observations. VQ-BeT augments BeT by tokenizing continuous actions with a hierarchical vector quantization module. Across seven environments including simulated manipulation, autonomous driving, and robotics, VQ-BeT improves on state-of-the-art models such as BeT and Diffusion Policies. Importantly, we demonstrate VQ-BeT's improved ability to capture behavior modes while accelerating inference speed 5x over Diffusion Policies. Videos and code can be found https://sjlee.cc/vq-bet, Comment: Github repo: https://github.com/jayLEE0301/vq_bet_official

Reinforcement learning (RL) often faces the challenges of uninformed search problems where the agent should explore without access to the domain knowledge such as characteristics of the environment or external rewards. To tackle these challenges, this work proposes a new approach for curriculum RL called Diversify for Disagreement & Conquer (D2C). Unlike previous curriculum learning methods, D2C requires only a few examples of desired outcomes and works in any environment, regardless of its geometry or the distribution of the desired outcome examples. The proposed method performs diversification of the goal-conditional classifiers to identify similarities between visited and desired outcome states and ensures that the classifiers disagree on states from out-of-distribution, which enables quantifying the unexplored region and designing an arbitrary goal-conditioned intrinsic reward signal in a simple and intuitive way. The proposed method then employs bipartite matching to define a curriculum learning objective that produces a sequence of well-adjusted intermediate goals, which enable the agent to automatically explore and conquer the unexplored region. We present experimental results demonstrating that D2C outperforms prior curriculum RL methods in both quantitative and qualitative aspects, even with the arbitrarily distributed desired outcome examples.

Recent curriculum Reinforcement Learning (RL) has shown notable progress in solving complex tasks by proposing sequences of surrogate tasks. However, the previous approaches often face challenges when they generate curriculum goals in a high-dimensional space. Thus, they usually rely on manually specified goal spaces. To alleviate this limitation and improve the scalability of the curriculum, we propose a novel curriculum method that automatically defines the semantic goal space which contains vital information for the curriculum process, and suggests curriculum goals over it. To define the semantic goal space, our method discretizes continuous observations via vector quantized-variational autoencoders (VQ-VAE) and restores the temporal relations between the discretized observations by a graph. Concurrently, ours suggests uncertainty and temporal distance-aware curriculum goals that converges to the final goals over the automatically composed goal space. We demonstrate that the proposed method allows efficient explorations in an uninformed environment with raw goal examples only. Also, ours outperforms the state-of-the-art curriculum RL methods on data efficiency and performance, in various goal-reaching tasks even with ego-centric visual inputs., Comment: Accepted to NeurIPS 2023

Deploying multiple robots for target search and tracking has many practical applications, yet the challenge of planning over unknown or partially known targets remains difficult to address. With recent advances in deep learning, intelligent control techniques such as reinforcement learning have enabled agents to learn autonomously from environment interactions with little to no prior knowledge. Such methods can address the exploration-exploitation tradeoff of planning over unknown targets in a data-driven manner, eliminating the reliance on heuristics typical of traditional approaches and streamlining the decision-making pipeline with end-to-end training. In this paper, we propose a multi-agent reinforcement learning technique with target map building based on distributed Gaussian process. We leverage the distributed Gaussian process to encode belief over the target locations and efficiently plan over unknown targets. We evaluate the performance and transferability of the trained policy in simulation and demonstrate the method on a swarm of micro unmanned aerial vehicles with hardware experiments., Comment: 10 pages, 6 figures; preprint submitted to IJCAS; first two authors contributed equally

For safe vision-based control applications, perception-related constraints have to be satisfied in addition to other state constraints. In this paper, we deal with the problem where a multirotor equipped with a camera needs to maintain the visibility of a point of interest while tracking a reference given by a high-level planner. We devise a method based on reference governor that, differently from existing solutions, is able to enforce control-level visibility constraints with theoretically assured feasibility. To this end, we design a new type of reference governor for linear systems with polynomial constraints which is capable of handling time-varying references. The proposed solution is implemented online for the real-time multirotor control with visibility constraints and validated with simulations and an actual hardware experiment., Comment: 8 pages, 6 figures, Accepted to 62nd IEEE Conference on Decision and Control (CDC 2023)

This study presents a framework to guarantee safety for a class of second-order nonlinear systems under multiple state and input constraints. To facilitate real-world applications, a safety-critical controller must consider multiple constraints simultaneously, while being able to impose general forms of constraints designed for various tasks (e.g., obstacle avoidance). With this in mind, we first devise a zeroing control barrier function (ZCBF) using a newly proposed nominal evading maneuver. By designing the nominal evading maneuver to 1) be continuously differentiable, 2) satisfy input constraints, and 3) be capable of handling other state constraints, we deduce an ultimate invariant set, a subset of the safe set that can be rendered forward invariant with admissible control inputs. Thanks to the development of the ultimate invariant set, we then propose a safety-critical controller, which is a computationally tractable one-step model predictive controller (MPC) with guaranteed recursive feasibility. We validate the proposed framework in simulation, where a fixed-wing UAV tracks a circular trajectory while satisfying multiple safety constraints including collision avoidance, bounds on flight speed and flight path angle, and input constraints., Comment: Accepted for the 2023 62nd IEEE Conference on Decision and Control (CDC)

This study presents a new hardware design and control of a minimally actuated 5 control degrees of freedom (CDoF) quadrotor-based tiltrotor. The proposed tiltrotor possesses several characteristics distinct from those found in existing works, including: 1) minimal number of actuators for 5 CDoF, 2) large margin to generate interaction force during aerial physical interaction (APhI), and 3) no mechanical obstruction in thrust direction rotation. Thanks to these properties, the proposed tiltrotor is suitable for perching-enabled APhI since it can hover parallel to an arbitrarily oriented surface and can freely adjust its thrust direction. To fully control the 5-CDoF of the designed tiltrotor, we construct an asymptotically stabilizing controller with stability analysis. The proposed tiltrotor design and controller are validated in experiments where the first two experiments of $x,y$ position tracking and pitch tracking show controllability of the added CDoF compared to a conventional quadrotor. Finally, the last experiment of perching and cart pushing demonstrates the proposed tiltrotor's applicability to perching-enabled APhI., Comment: 7 pages, 10 figures, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) accepted

While reinforcement learning (RL) has achieved great success in acquiring complex skills solely from environmental interactions, it assumes that resets to the initial state are readily available at the end of each episode. Such an assumption hinders the autonomous learning of embodied agents due to the time-consuming and cumbersome workarounds for resetting in the physical world. Hence, there has been a growing interest in autonomous RL (ARL) methods that are capable of learning from non-episodic interactions. However, existing works on ARL are limited by their reliance on prior data and are unable to learn in environments where task-relevant interactions are sparse. In contrast, we propose a demonstration-free ARL algorithm via Implicit and Bi-directional Curriculum (IBC). With an auxiliary agent that is conditionally activated upon learning progress and a bidirectional goal curriculum based on optimal transport, our method outperforms previous methods, even the ones that leverage demonstrations., Comment: ICML 2023, first two authors contributed equally

The objective of the image inpainting task is to fill missing regions of an image in a visually plausible way. Recently, deep-learning-based image inpainting networks have generated outstanding results, and some utilize their models as object removers by masking unwanted objects in an image. However, while trying to better remove objects using their networks, the previous works pay less attention to the importance of the input mask. In this paper, we focus on generating the input mask to better remove objects using the off-the-shelf image inpainting network. We propose an automatic mask generator inspired by the explainable AI (XAI) method, whose output can better remove objects than a semantic segmentation mask. The proposed method generates an importance map using randomly sampled input masks and quantitatively estimated scores of the completed images obtained from the random masks. The output mask is selected by a judge module among the candidate masks which are generated from the importance map. We design the judge module to quantitatively estimate the quality of the object removal results. In addition, we empirically find that the evaluation methods used in the previous works reporting object removal results are not appropriate for estimating the performance of an object remover. Therefore, we propose new evaluation metrics (FID$^*$ and U-IDS$^*$) to properly evaluate the quality of object removers. Experiments confirm that our method shows better performance in removing target class objects than the masks generated from the semantic segmentation maps, and the two proposed metrics make judgments consistent with humans.

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., Comment: This paper has been accepted to ICRA 2023

Maintaining the visibility of the targets is one of the major objectives of aerial tracking applications. This paper proposes QP Chaser, a trajectory planning pipeline that can enhance the visibility of single- and dual-target in both static and dynamic environments. As the name suggests, the proposed planner generates a target-visible trajectory via quadratic programming problems. First, the predictor forecasts the reachable sets of moving objects with a sample-and-check strategy considering obstacles. Subsequently, the trajectory planner reinforces the visibility of targets with consideration of 1) path topology and 2) reachable sets of targets and obstacles. We define a target-visible region (TVR) with topology analysis of not only static obstacles but also dynamic obstacles, and it reflects reachable sets of moving targets and obstacles to maintain the whole body of the target within the camera image robustly and ceaselessly. The online performance of the proposed planner is validated in multiple scenarios, including high-fidelity simulations and real-world experiments., Comment: 15 pages, 13 figures

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a sequence of surrogate tasks, shows reasonable results, most of the previous works still have difficulty in proposing curriculum due to the absence of a mechanism for obtaining calibrated guidance to the desired outcome state without any prior domain knowledge. To alleviate it, we propose an uncertainty & temporal distance-aware curriculum goal generation method for the outcome-directed RL via solving a bipartite matching problem. It could not only provide precisely calibrated guidance of the curriculum to the desired outcome states but also bring much better sample efficiency and geometry-agnostic curriculum goal proposal capability compared to previous curriculum RL methods. We demonstrate that our algorithm significantly outperforms these prior methods in a variety of challenging navigation tasks and robotic manipulation tasks in a quantitative and qualitative way., Comment: ICLR 2023 Spotlight. First two authors contributed equally

As previous representations for reinforcement learning cannot effectively incorporate a human-intuitive understanding of the 3D environment, they usually suffer from sub-optimal performances. In this paper, we present Semantic-aware Neural Radiance Fields for Reinforcement Learning (SNeRL), which jointly optimizes semantic-aware neural radiance fields (NeRF) with a convolutional encoder to learn 3D-aware neural implicit representation from multi-view images. We introduce 3D semantic and distilled feature fields in parallel to the RGB radiance fields in NeRF to learn semantic and object-centric representation for reinforcement learning. SNeRL outperforms not only previous pixel-based representations but also recent 3D-aware representations both in model-free and model-based reinforcement learning., Comment: ICML 2023. First two authors contributed equally. Order was determined by coin flip

This study aims to design a motion/force controller for an aerial manipulator which guarantees the tracking of time-varying motion/force trajectories as well as the stability during the transition between free and contact motions. To this end, we model the force exerted on the end-effector as the Kelvin-Voigt linear model and estimate its parameters by recursive least-squares estimator. Then, the gains of the disturbance-observer (DOB)-based motion/force controller are calculated based on the stability conditions considering both the model uncertainties in the dynamic equation and switching between the free and contact motions. To validate the proposed controller, we conducted the time-varying motion/force tracking experiments with different approach speeds and orientations of the surface. The results show that our controller enables the aerial manipulator to track the time-varying motion/force trajectories., Comment: to be presented in 2023 IEEE International Conference on Robotics and Automations (ICRA), London, United Kingdom, 2023

Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection. Recently, learning-based algorithms achieve huge success in depth estimation by training models with a large amount of data in a supervised manner. However, it is challenging to acquire dense ground truth depth labels for supervised training, and the unsupervised depth estimation using monocular sequences emerges as a promising alternative. Unfortunately, most studies on unsupervised depth estimation explore loss functions or occlusion masks, and there is little change in model architecture in that ConvNet-based encoder-decoder structure becomes a de-facto standard for depth estimation. In this paper, we employ a convolution-free Swin Transformer as an image feature extractor so that the network can capture both local geometric features and global semantic features for depth estimation. Also, we propose a Densely Cascaded Multi-scale Network (DCMNet) that connects every feature map directly with another from different scales via a top-down cascade pathway. This densely cascaded connectivity reinforces the interconnection between decoding layers and produces high-quality multi-scale depth outputs. The experiments on two different datasets, KITTI and Make3D, demonstrate that our proposed method outperforms existing state-of-the-art unsupervised algorithms., Comment: ICRA 2023

Thanks to the development of 2D keypoint detectors, monocular 3D human pose estimation (HPE) via 2D-to-3D uplifting approaches have achieved remarkable improvements. Still, monocular 3D HPE is a challenging problem due to the inherent depth ambiguities and occlusions. To handle this problem, many previous works exploit temporal information to mitigate such difficulties. However, there are many real-world applications where frame sequences are not accessible. This paper focuses on reconstructing a 3D pose from a single 2D keypoint detection. Rather than exploiting temporal information, we alleviate the depth ambiguity by generating multiple 3D pose candidates which can be mapped to an identical 2D keypoint. We build a novel diffusion-based framework to effectively sample diverse 3D poses from an off-the-shelf 2D detector. By considering the correlation between human joints by replacing the conventional denoising U-Net with graph convolutional network, our approach accomplishes further performance improvements. We evaluate our method on the widely adopted Human3.6M and HumanEva-I datasets. Comprehensive experiments are conducted to prove the efficacy of the proposed method, and they confirm that our model outperforms state-of-the-art multi-hypothesis 3D HPE methods., Comment: Accepted to IROS 2023. First two authors contributed equally

Hierarchical Reinforcement Learning (HRL) has made notable progress in complex control tasks by leveraging temporal abstraction. However, previous HRL algorithms often suffer from serious data inefficiency as environments get large. The extended components, $i.e.$, goal space and length of episodes, impose a burden on either one or both high-level and low-level policies since both levels share the total horizon of the episode. In this paper, we present a method of Decoupling Horizons Using a Graph in Hierarchical Reinforcement Learning (DHRL) which can alleviate this problem by decoupling the horizons of high-level and low-level policies and bridging the gap between the length of both horizons using a graph. DHRL provides a freely stretchable high-level action interval, which facilitates longer temporal abstraction and faster training in complex tasks. Our method outperforms state-of-the-art HRL algorithms in typical HRL environments. Moreover, DHRL achieves long and complex locomotion and manipulation tasks., Comment: Accepted to NeurIPS 2022 (Selected as Oral)

Offline reinforcement learning (Offline RL) suffers from the innate distributional shift as it cannot interact with the physical environment during training. To alleviate such limitation, state-based offline RL leverages a learned dynamics model from the logged experience and augments the predicted state transition to extend the data distribution. For exploiting such benefit also on the image-based RL, we firstly propose a generative model, S2P (State2Pixel), which synthesizes the raw pixel of the agent from its corresponding state. It enables bridging the gap between the state and the image domain in RL algorithms, and virtually exploring unseen image distribution via model-based transition in the state space. Through experiments, we confirm that our S2P-based image synthesis not only improves the image-based offline RL performance but also shows powerful generalization capability on unseen tasks., Comment: NeurIPS 2022, first two authors contributed equally

This paper presents a decentralized multi-agent trajectory planning (MATP) algorithm that guarantees to generate a safe, deadlock-free trajectory in an obstacle-rich environment under a limited communication range. The proposed algorithm utilizes a grid-based multi-agent path planning (MAPP) algorithm for deadlock resolution, and we introduce the subgoal optimization method to make the agent converge to the waypoint generated from the MAPP without deadlock. In addition, the proposed algorithm ensures the feasibility of the optimization problem and collision avoidance by adopting a linear safe corridor (LSC). We verify that the proposed algorithm does not cause a deadlock in both random forests and dense mazes regardless of communication range, and it outperforms our previous work in flight time and distance. We validate the proposed algorithm through a hardware demonstration with ten quadrotors., Comment: 11 pages, extended version of conference version

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent in a task-agnostic manner without access to the task-specific reward, leverages active exploration for distilling diverse experience into essential skills or reusable knowledge. For exploiting such benefits also in robotic manipulation, we propose an unsupervised method for transferable manipulation skill discovery that ties structured exploration toward interacting behavior and transferable skill learning. It not only enables the agent to learn interaction behavior, the key aspect of the robotic manipulation learning, without access to the environment reward, but also to generalize to arbitrary downstream manipulation tasks with the learned task-agnostic skills. Through comparative experiments, we show that our approach achieves the most diverse interacting behavior and significantly improves sample efficiency in downstream tasks including the extension to multi-object, multitask problems., Comment: 8 pages, 9 figures; accepted for publication in the IEEE Robotics and Automation Letters (RA-L); supplementary video available at https://www.youtube.com/watch?v=bF3Y4WXfM7c&t=9s

Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent resets to a fixed initial state distribution at the end of each episode, to successfully train the agents from repeated trials. Such reset mechanism, while trivial for simulated tasks, can be challenging to provide for real-world robotics tasks. Resets in robotic systems often require extensive human supervision and task-specific workarounds, which contradicts the goal of autonomous robot learning. In this paper, we propose an extension to conventional reinforcement learning towards greater autonomy by introducing an additional agent that learns to reset in a self-supervised manner. The reset agent preemptively triggers a reset to prevent manual resets and implicitly imposes a curriculum for the forward agent. We apply our method to learn from scratch on a suite of simulated and real-world continuous control tasks and demonstrate that the reset agent successfully learns to reduce manual resets whilst also allowing the forward policy to improve gradually over time., Comment: 8 pages, 6 figures; accepted for publication in the IEEE Robotics and Automation Letters (RA-L); source code available at https://github.com/jigangkim/autoreset_rl ; supplementary video available at https://youtu.be/himd0Z5b64A

This paper proposes a cooperative environmental learning algorithm working in a fully distributed manner. A multi-robot system is more effective for exploration tasks than a single robot, but it involves the following challenges: 1) online distributed learning of environmental map using multiple robots; 2) generation of safe and efficient exploration path based on the learned map; and 3) maintenance of the scalability with respect to the number of robots. To this end, we divide the entire process into two stages of environmental learning and path planning. Distributed algorithms are applied in each stage and combined through communication between adjacent robots. The environmental learning algorithm uses a distributed Gaussian process, and the path planning algorithm uses a distributed Monte Carlo tree search. As a result, we build a scalable system without the constraint on the number of robots. Simulation results demonstrate the performance and scalability of the proposed system. Moreover, a real-world-dataset-based simulation validates the utility of our algorithm in a more realistic scenario.

Rapidly generating an optimal chasing motion of a drone to follow a dynamic target among obstacles is challenging due to numerical issues rising from multiple conflicting objectives and non-convex constraints. This study proposes to resolve the difficulties with a fast and reliable pipeline that incorporates 1) a target movement forecaster and 2) a chasing planner. They are based on a sample-and-check approach that consists of the generation of high-quality candidate primitives and the feasibility tests with a light computation load. We forecast the movement of the target by selecting an optimal prediction among a set of candidates built from past observations. Based on the prediction, we construct a set of prospective chasing trajectories which reduce the high-order derivatives, while maintaining the desired relative distance from the predicted target movement. Then, the candidate trajectories are tested on safety of the chaser and visibility toward the target without loose approximation of the constraints. The proposed algorithm is thoroughly evaluated in challenging scenarios involving dynamic obstacles. Also, the overall process from the target recognition to the chasing motion planning is implemented fully onboard on a drone, demonstrating real-world applicability., Comment: 10 pages

This paper presents a new online multi-agent trajectory planning algorithm that guarantees to generate safe, dynamically feasible trajectories in a cluttered environment. The proposed algorithm utilizes a linear safe corridor (LSC) to formulate the distributed trajectory optimization problem with only feasible constraints, so it does not resort to slack variables or soft constraints to avoid optimization failure. We adopt a priority-based goal planning method to prevent the deadlock without an additional procedure to decide which robot to yield. The proposed algorithm can compute the trajectories for 60 agents on average 15.5 ms per agent with an Intel i7 laptop and shows a similar flight distance and distance compared to the baselines based on soft constraints. We verified that the proposed method can reach the goal without deadlock in both the random forest and the indoor space, and we validated the safety and operability of the proposed algorithm through a real flight test with ten quadrotors in a maze-like environment., Comment: 8 pages, RA-L 2022 under review

Visual navigation has been widely used for state estimation of micro aerial vehicles (MAVs). For stable visual navigation, MAVs should generate perception-aware paths which guarantee enough visible landmarks. Many previous works on perception-aware path planning focused on sampling-based planners. However, they may suffer from sample inefficiency, which leads to computational burden for finding a global optimal path. To address this issue, we suggest a perception-aware path planner which utilizes topological information of environments. Since the topological class of a path and visible landmarks during traveling the path are closely related, the proposed algorithm checks distinctive topological classes to choose the class with abundant visual information. Topological graph is extracted from the generalized Voronoi diagram of the environment and initial paths with different topological classes are found. To evaluate the perception quality of the classes, we divide the initial path into discrete segments where the points in each segment share similar visual information. The optimal class with high perception quality is selected, and a graph-based planner is utilized to generate path within the class. With simulations and real-world experiments, we confirmed that the proposed method could guarantee accurate visual navigation compared with the perception-agnostic method while showing improved computational efficiency than the sampling-based perception-aware planner., Comment: 8 pages, 9 figures, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) accepted

Motion planners for mobile robots in unknown environments face the challenge of simultaneously maintaining both robustness against unmodeled uncertainties and persistent feasibility of the trajectory-finding problem. That is, while dealing with uncertainties, a motion planner must update its trajectory, adapting to the newly revealed environment in real-time; failing to do so may involve unsafe circumstances. Many existing planning algorithms guarantee these by maintaining the clearance needed to perform an emergency brake, which is itself a robust and persistently feasible maneuver. However, such maneuvers are not applicable for systems in which braking is impossible or risky, such as fixed-wing aircraft. To that end, we propose a real-time robust planner that recursively guarantees persistent feasibility without any need of braking. The planner ensures robustness against bounded uncertainties and persistent feasibility by constructing a loop of sequentially composed funnels, starting from the receding horizon local trajectory's forward reachable set. We implement the proposed algorithm for a robotic car tracking a speed-fixed reference trajectory. The experiment results show that the proposed algorithm can be run at faster than 16 Hz, while successfully keeping the system away from entering any dead-end, to maintain safety and feasibility., Comment: 8 pages, 11 figures, 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) accepted