Pinxin Long, Tingxiang Fan, Xinyi Liao, Wenxi Liu, Hao Zhang, Jia Pan
Developing a safe and efficient collision avoidance policy for multiple robots is challenging in the decentralized scenarios where each robot generate its paths without observing other robots' states and intents. While other distributed multi-robot collision avoidance systems exist, they often require extracting agent-level features to plan a local collision-free action, which can be computationally prohibitive and not robust. More importantly, in practice the performance of these methods are much lower than their centralized counterparts. We present a decentralized sensor-level collision avoidance policy for multi-robot systems, which directly maps raw sensor measurements to an agent's steering commands in terms of movement velocity. As a first step toward reducing the performance gap between decentralized and centralized methods, we present a multi-scenario multi-stage training framework to find an optimal policy which is trained over a large number of robots on rich, complex environments simultaneously using a policy gradient based reinforcement learning algorithm. We validate the learned sensor-level collision avoidance policy in a variety of simulated scenarios with thorough performance evaluations and show that the final learned policy is able to find time efficient, collision-free paths for a large-scale robot system. We also demonstrate that the learned policy can be well generalized to new scenarios that do not appear in the entire training period, including navigating a heterogeneous group of robots and a large-scale scenario with 100 robots. Videos are available at https://sites.google.com/view/drlmaca
Hao Zhang, Pinxin Long, Dandan Zhou, Zhongfeng Qian, Zheng Wang, Weiwei Wan, Dinesh Manocha, Chonhyon Park, Tommy Hu, Chao Cao, Yibo Chen, Marco Chow, Jia Pan
Robots that autonomously manipulate objects within warehouses have the potential to shorten the package delivery time and improve the efficiency of the e-commerce industry. In this paper, we present a robotic system that is capable of both picking and placing general objects in warehouse scenarios. Given a target object, the robot autonomously detects it from a shelf or a table and estimates its full 6D pose. With this pose information, the robot picks the object using its gripper, and then places it into a container or at a specified location. We describe our pick-and-place system in detail while highlighting our design principles for the warehouse settings, including the perception method that leverages knowledge about its workspace, three grippers designed to handle a large variety of different objects in terms of shape, weight and material, and grasp planning in cluttered scenarios. We also present extensive experiments to evaluate the performance of our picking system and demonstrate that the robot is competent to accomplish various tasks in warehouse settings, such as picking a target item from a tight space, grasping different objects from the shelf, and performing pick-and-place tasks on the table.
Tingxiang Fan, Xinjing Cheng, Jia Pan, Dinesh Manocha, Ruigang Yang
Navigation is an essential capability for mobile robots. In this paper, we propose a generalized yet effective 3M (i.e., multi-robot, multi-scenario, and multi-stage) training framework. We optimize a mapless navigation policy with a robust policy gradient algorithm. Our method enables different types of mobile platforms to navigate safely in complex and highly dynamic environments, such as pedestrian crowds. To demonstrate the superiority of our method, we test our methods with four kinds of mobile platforms in four scenarios. Videos are available at https://sites.google.com/view/crowdmove.
Biao Jia, Zhe Hu, Zherong Pan, Dinesh Manocha, Jia Pan
In this paper, we present a general learning-based framework to automatically visual-servo control the position and shape of a deformable object with unknown deformation parameters. The servo-control is accomplished by learning a feedback controller that determines the robotic end-effector's movement according to the deformable object's current status. This status encodes the object's deformation behavior by using a set of observed visual features, which are either manually designed or automatically extracted from the robot's sensor stream. A feedback control policy is then optimized to push the object toward a desired featured status efficiently. The feedback policy can be learned either online or offline. Our online policy learning is based on the Gaussian Process Regression (GPR), which can achieve fast and accurate manipulation and is robust to small perturbations. An offline imitation learning framework is also proposed to achieve a control policy that is robust to large perturbations in the human-robot interaction. We validate the performance of our controller on a set of deformable object manipulation tasks and demonstrate that our method can achieve effective and accurate servo-control for general deformable objects with a wide variety of goal settings.
Liang He, Jia Pan, Danwei Li, Dinesh Manocha
We present a novel method to compute the approximate global penetration depth (PD) between two non-convex geometric models. Our approach consists of two phases: offline precomputation and run-time queries. In the first phase, our formulation uses a novel sampling algorithm to precompute an approximation of the high-dimensional contact space between the pair of models. As compared with prior random sampling algorithms for contact space approximation, our propagation sampling considerably speeds up the precomputation and yields a high quality approximation. At run-time, we perform a nearest-neighbor query and local projection to efficiently compute the translational or generalized PD. We demonstrate the performance of our approach on complex 3D benchmarks with tens or hundreds of thousands of triangles, and we observe significant improvement over previous methods in terms of accuracy, with a modest improvement in the run-time performance.
Pinxin Long, Wenxi Liu, Jia Pan
High-speed, low-latency obstacle avoidance that is insensitive to sensor noise is essential for enabling multiple decentralized robots to function reliably in cluttered and dynamic environments. While other distributed multi-agent collision avoidance systems exist, these systems require online geometric optimization where tedious parameter tuning and perfect sensing are necessary. We present a novel end-to-end framework to generate reactive collision avoidance policy for efficient distributed multi-agent navigation. Our method formulates an agent's navigation strategy as a deep neural network mapping from the observed noisy sensor measurements to the agent's steering commands in terms of movement velocity. We train the network on a large number of frames of collision avoidance data collected by repeatedly running a multi-agent simulator with different parameter settings. We validate the learned deep neural network policy in a set of simulated and real scenarios with noisy measurements and demonstrate that our method is able to generate a robust navigation strategy that is insensitive to imperfect sensing and works reliably in all situations. We also show that our method can be well generalized to scenarios that do not appear in our training data, including scenes with static obstacles and agents with different sizes. Videos are available at https://sites.google.com/view/deepmaca.
Yajue Yang, Yuanqing Wu, Jia Pan
We propose a novel unifying scheme for parallel implementation of articulated robot dynamics algorithms. It is based on a unified Lie group notation for deriving the equations of motion of articulated robots, where various well-known forward algorithms differ only by their joint inertia matrix inversion strategies. This new scheme leads to a unified abstraction of state-of-the-art forward dynamics algorithms into combinations of block bi-diagonal and/or block tri-diagonal systems, which may be efficiently solved by parallel all-prefix-sum operations (scan) and parallel odd-even elimination (OEE) respectively. We implement the proposed scheme on a Nvidia CUDA GPU platform for the comparative study of three algorithms, namely the hybrid articulated-body inertia algorithm (ABIA), the parallel joint space inertia inversion algorithm (JSIIA) and the constrained force algorithm (CFA), and the performances are analyzed.
Yajue Yang, Yuanqing Wu, Jia Pan
We propose a new parallel framework for fast computation of inverse and forward dynamics of articulated robots based on prefix sums (scans). We re-investigate the well-known recursive Newton-Euler formulation of robot dynamics and show that the forward-backward propagation process for robot inverse dynamics is equivalent to two scan operations on certain semigroups. We show that the state-of-the-art forward dynamics algorithms may almost completely be cast into a sequence of scan operations, with unscannable parts clearly identified. This suggests a serial-parallel hybrid approach for systems with a moderate number of links. We implement our scan based algorithms on Nvidia CUDA platform with performance compared with multithreading CPU-based recursive algorithms; a significant level of acceleration is demonstrated.
Liang He, Jia Pan, Sahil Narang, Wenping Wang, Dinesh Manocha
We present a new algorithm to simulate dynamic group behaviors for interactive multi-agent crowd simulation. Our approach is general and makes no assumption about the environment, shape, or size of the groups. We use the least effort principle to perform coherent group navigation and present efficient inter-group and intra-group maintenance techniques. We extend the reciprocal collision avoidance scheme to perform agent-group and group-group collision avoidance that can generate collision-free as well as coherent and trajectories. The additional overhead of dynamic group simulation is relatively small. We highlight its interactive performance on complex scenarios with hundreds of agents and compare the trajectory behaviors with real-world videos.
Chao Cao, Weiwei Wan, Jia Pan, Kensuke Harada
Pick-and-place regrasp is an important manipulation skill for a robot. It helps a robot accomplish tasks that cannot be achieved within a single grasp, due to constraints such as kinematics or collisions between the robot and the environment. Previous work on pick-and-place regrasp only leveraged flat surfaces for intermediate placements, and thus is limited in the capability to reorient an object. In this paper, we extend the reorientation capability of a pick-and-place regrasp by adding a vertical pin on the working surface and using it as the intermediate location for regrasping. In particular, our method automatically computes the stable placements of an object leaning against a vertical pin, finds several force-closure grasps, generates a graph of regrasp actions, and searches for the regrasp sequence. To compare the regrasping performance with and without using pins, we evaluate the success rate and the length of regrasp sequences while performing tasks on various models. Experiments on reorientation and assembly tasks validate the benefit of using support pins for regrasping.
Jiaming Qi, Peng Zhou, Pai Zheng, Hongmin Wu, Chenguang Yang, David Navarro-Alarcon, Jia Pan
Bagging operations, common in packaging and assisted living applications, are challenging due to a bag's complex deformable properties. To address this, we develop a robotic system for automated bagging tasks using an adaptive structure-of-interest (SOI) manipulation approach. Our method relies on real-time visual feedback to dynamically adjust manipulation without requiring prior knowledge of bag materials or dynamics. We present a robust pipeline featuring state estimation for SOIs using Gaussian Mixture Models (GMM), SOI generation via optimization-based bagging techniques, SOI motion planning with Constrained Bidirectional Rapidly-exploring Random Trees (CBiRRT), and dual-arm manipulation coordinated by Model Predictive Control (MPC). Experiments demonstrate the system's ability to achieve precise, stable bagging of various objects using adaptive coordination of the manipulators. The proposed framework advances the capability of dual-arm robots to perform more sophisticated automation of common tasks involving interactions with deformable objects.
Pan Jia, Mo Zhou, Haiping Yu, Cunjing Lv, Guangyin Jing
Escaping of the liquid molecules from their liquid bulk into the vapour phase at the vapour-liquid interface is controlled by the vapour diffusion process, which nevertheless hardly senses the macroscopic shape of this interface. Here, deformed sessile drops due to gravity and surface tension with various interfacial profiles are realised by tilting flat substrates. The symmetry broken of the sessile drop geometry leads to a different evaporation behavior compared to a drop with a symmetric cap on a horizontal substrate. Rather than the vapour-diffusion mechanism, heat-diffusion regime is defined here to calculate the local evaporation flux along the deformed drop interface. A local heat resistance, characterised by the liquid layer thickness perpendicular to the substrate, is proposed to relate the local evaporation flux. We find that the drops with and without deformation evaporate with a minimum flux at the drop apex, while up to a maximum one with a significantly larger but finite value at the contact line. Counterintuitively, the deviation from the symmetric shape due to the deformation on a slope, surprisingly enhances the total evaporation rate; and the smaller contact angle, the more significant enhancement. Larger tilt quickens the overall evaporation process and induces a more heterogeneous distribution of evaporative flux under gravity. Interestingly, with this concept of heat flux, an intrinsic heat resistance is conceivable around the contact line, which naturally removes the singularity of the evaporation flux showing in the vapour-diffusion model. The detailed non-uniform evaporation flux suggests ways to control the self-assembly, microstructures of deposit with engineering applications particularly in three dimensional printing where drying on slopes is inevitable.
Xuan Zhao, Jia Pan
It is well-known that a deep understanding of co-workers' behavior and preference is important for collaboration effectiveness. In this work, we present a method to accomplish smooth human-robot collaboration in close proximity by taking into account the human's behavior while planning the robot's trajectory. In particular, we first use an occupancy map to summarize human's movement preference over time, and such prior information is then considered in an optimization-based motion planner via two cost items as introduced in [1]: 1) avoidance of the workspace previously occupied by human, to eliminate the interruption and to increase the task success rate; 2) tendency to keep a safe distance between the human and the robot to improve the safety. In the experiments, we compare the collaboration performance among planners using different combinations of human-aware cost items, including the avoidance factor, both the avoidance and safe distance factor, and a baseline where no human-related factors are considered. The trajectories generated are tested in both simulated and real-world environments, and the results show that our method can significantly increase the collaborative task success rates and is also human-friendly. Our experimental results also show that the cost functions need to be adjusted in a task specific manner to better reflect human's preference.
Pan Jia, Bruno Andreotti, Philippe Claudin
A flexible sheet clamped at both ends and submitted to a permanent wind is unstable and propagates waves. Here, we experimentally study the selection of frequency and wavenumber as a function of the wind velocity. These quantities obey simple scaling laws, which are analytically derived from a linear stability analysis of the problem, and which also involve a gravity-induced velocity scale. This approach allows us to collapse data obtained with sheets whose flexible rigidity is varied by two orders of magnitude. This principle may be applied in the future for energy harvesting.
Tao Han, Xuan Zhao, Peigen Sun, Jia Pan
Existing shape estimation methods for deformable object manipulation suffer from the drawbacks of being off-line, model dependent, noise-sensitive or occlusion-sensitive, and thus are not appropriate for manipulation tasks requiring high precision. In this paper, we present a real-time shape estimation approach for autonomous robotic manipulation of 3D deformable objects. Our method fulfills all the requirements necessary for the high-quality deformable object manipulation in terms of being real-time, model-free and robust to noise and occlusion. These advantages are accomplished using a joint tracking and reconstruction framework, in which we track the object deformation by aligning a reference shape model with the stream input from the RGB-D camera, and simultaneously upgrade the reference shape model according to the newly captured RGB-D data. We have evaluated the quality and robustness of our real-time shape estimation pipeline on a set of deformable manipulation tasks implemented on physical robots. Videos are available at https://lifeisfantastic.github.io/DeformShapeEst/
Zhe Hu, Jia Pan, Tingxiang Fan, Ruigang Yang, Dinesh Manocha
In this paper, we present a robotic navigation algorithm with natural language interfaces, which enables a robot to safely walk through a changing environment with moving persons by following human instructions such as "go to the restaurant and keep away from people". We first classify human instructions into three types: the goal, the constraints, and uninformative phrases. Next, we provide grounding for the extracted goal and constraint items in a dynamic manner along with the navigation process, to deal with the target objects that are too far away for sensor observation and the appearance of moving obstacles like humans. In particular, for a goal phrase (e.g., "go to the restaurant"), we ground it to a location in a predefined semantic map and treat it as a goal for a global motion planner, which plans a collision-free path in the workspace for the robot to follow. For a constraint phrase (e.g., "keep away from people"), we dynamically add the corresponding constraint into a local planner by adjusting the values of a local costmap according to the results returned by the object detection module. The updated costmap is then used to compute a local collision avoidance control for the safe navigation of the robot. By combining natural language processing, motion planning, and computer vision, our developed system is demonstrated to be able to successfully follow natural language navigation instructions to achieve navigation tasks in both simulated and real-world scenarios. Videos are available at https://sites.google.com/view/snhi
Zhong Zhang, Tao Han, Jia Pan, Zheng Wang
To achieve human-like dexterity for anthropomorphic robotic hands, it is essential to understand the biomechanics and control strategies of the human hand, in order to reduce the number of actuators being used without loosing hand flexibility. To this end, in this article, we propose a new interpretation about the working mechanism of the metacarpal (MCP) joint's extension and the underlying control strategies of the human hand, based on which we further propose a highly flexible finger design to achieve independent movements of interphalangeal (IP) joints and MCP joint. Besides, we consider the hyperextension of fingertip into our design which helps robotic finger present compliant and adaptive posture for touching and pinching. In addition, human thumb muscle functions are reconstructed in the proposed robotic hand design, by replacing 9 human muscle tendons with 3 cables in the proposed task-oriented design, realizing all 33 static and stable grasping postures. Videos are available at https://sites.google.com/view/szwd
Pan Jia, Bruno Andreotti, Philippe Claudin
Turbulent flows above a solid surface are characterised by a hydrodynamic roughness that represents, for the far velocity field, the typical length scale at which momentum mixing occurs close to the surface. Here, we are theoretically interested in the hydrodynamic roughness induced by a two-dimensional modulated surface, the elevation profile of which is decomposed in Fourier modes. We describe the flow for a sinusoidal mode of given wavelength and amplitude with RANS equations closed by means of a mixing-length approach that takes into account a possible surface geometrical roughness as well as the presence of a viscous sublayer. It also incorporates spatial transient effects at the laminar-turbulent transition. Performing a weekly non-linear expansion in the bedform aspect ratio, we predict the effective hydrodynamic roughness when the surface wavelength is varied and we show that it presents a non-monotonic behaviour at the laminar-turbulent transition when the surface is hydrodynamically smooth. Further, with a self-consistent looped calculation, we are able to recover the smooth-rough transition of a flat surface, for which the hydrodynamic roughness changes from a regime where it is dominated by the viscous length to another one where it scales with the surface corrugation. We finally apply the results to natural patterns resulted from hydrodynamic instabilities such as those associated with dissolution or sediment transport. We discuss in particular the aspect ratio selection of dissolution bedforms and roughness hierarchy in superimposed ripples and dunes.
Tingxiang Fan, Pinxin Long, Wenxi Liu, Jia Pan
In this paper, we present a decentralized sensor-level collision avoidance policy for multi-robot systems, which shows promising results in practical applications. In particular, our policy directly maps raw sensor measurements to an agent's steering commands in terms of the movement velocity. As a first step toward reducing the performance gap between decentralized and centralized methods, we present a multi-scenario multi-stage training framework to learn an optimal policy. The policy is trained over a large number of robots in rich, complex environments simultaneously using a policy gradient based reinforcement learning algorithm. The learning algorithm is also integrated into a hybrid control framework to further improve the policy's robustness and effectiveness. We validate the learned sensor-level collision avoidance policy in a variety of simulated and real-world scenarios with thorough performance evaluations for large-scale multi-robot systems. The generalization of the learned policy is verified in a set of unseen scenarios including the navigation of a group of heterogeneous robots and a large-scale scenario with 100 robots. Although the policy is trained using simulation data only, we have successfully deployed it on physical robots with shapes and dynamics characteristics that are different from the simulated agents, in order to demonstrate the controller's robustness against the sim-to-real modeling error. Finally, we show that the collision-avoidance policy learned from multi-robot navigation tasks provides an excellent solution to the safe and effective autonomous navigation for a single robot working in a dense real human crowd. Our learned policy enables a robot to make effective progress in a crowd without getting stuck. Videos are available at https://sites.google.com/view/hybridmrca
Tingxiang Fan, Xinjing Cheng, Jia Pan, Pinxin Long, Wenxi Liu, Ruigang Yang, Dinesh Manocha
We aim to enable a mobile robot to navigate through environments with dense crowds, e.g., shopping malls, canteens, train stations, or airport terminals. In these challenging environments, existing approaches suffer from two common problems: the robot may get frozen and cannot make any progress toward its goal, or it may get lost due to severe occlusions inside a crowd. Here we propose a navigation framework that handles the robot freezing and the navigation lost problems simultaneously. First, we enhance the robot's mobility and unfreeze the robot in the crowd using a reinforcement learning based local navigation policy developed in our previous work~\cite{long2017towards}, which naturally takes into account the coordination between the robot and the human. Secondly, the robot takes advantage of its excellent local mobility to recover from its localization failure. In particular, it dynamically chooses to approach a set of recovery positions with rich features. To the best of our knowledge, our method is the first approach that simultaneously solves the freezing problem and the navigation lost problem in dense crowds. We evaluate our method in both simulated and real-world environments and demonstrate that it outperforms the state-of-the-art approaches. Videos are available at https://sites.google.com/view/rlslam.