Robotics (cs.RO)

Abstract: Autonomous robotic systems, like autonomous vehicles and robotic search and rescue, require efficient on-device training for continuous adaptation of Deep Reinforcement Learning (DRL) models in dynamic environments. This research is fundamentally motivated by the need to understand and address the challenges of on-device real-time DRL, which involves balancing timing and algorithm performance under memory constraints, as exposed through our extensive empirical studies. This intricate balance requires co-optimizing two pivotal parameters of DRL training -- batch size and replay buffer size. Configuring these parameters significantly affects timing and algorithm performance, while both (unfortunately) require substantial memory allocation to achieve near-optimal performance. This paper presents R^3, a holistic solution for managing timing, memory, and algorithm performance in on-device real-time DRL training. R^3 employs (i) a deadline-driven feedback loop with dynamic batch sizing for optimizing timing, (ii) efficient memory management to reduce memory footprint and allow larger replay buffer sizes, and (iii) a runtime coordinator guided by heuristic analysis and a runtime profiler for dynamically adjusting memory resource reservations. These components collaboratively tackle the trade-offs in on-device DRL training, improving timing and algorithm performance while minimizing the risk of out-of-memory (OOM) errors. We implemented and evaluated R^3 extensively across various DRL frameworks and benchmarks on three hardware platforms commonly adopted by autonomous robotic systems. Additionally, we integrate R^3 with a popular realistic autonomous car simulator to demonstrate its real-world applicability. Evaluation results show that R^3 achieves efficacy across diverse platforms, ensuring consistent latency performance and timing predictability with minimal overhead.

Abstract: In this study, we present an optimization framework for efficient motion priority design between automated and teleoperated robots in an industrial recovery scenario. Although robots have recently become increasingly common in industrial sites, there are still challenges in achieving human-robot collaboration/cooperation (HRC), where human workers and robots are engaged in collaborative and cooperative tasks in a shared workspace. For example, the corresponding factory cell must be suspended for safety when an industrial robot drops an assembling part in the workspace. After that, a human worker is allowed to enter the robot workspace to address the robot recovery. This process causes non-continuous manufacturing, which leads to a productivity reduction. Recently, robotic teleoperation technology has emerged as a promising solution to enable people to perform tasks remotely and safely. This technology can be used in the recovery process in manufacturing failure scenarios. Our proposition involves the design of an appropriate priority function that aids in collision avoidance between the manufacturing and recovery robots and facilitates continuous processes with minimal production loss within an acceptable risk level. This paper presents a framework, including an HRC simulator and an optimization formulation, for finding optimal parameters of the priority function. Through quantitative and qualitative experiments, we address the proof of our novel concept and demonstrate its feasibility.

Abstract: With the development of information technology, robot technology has made great progress in various fields. These new technologies enable robots to be used in industry, agriculture, education and other aspects. In this paper, we propose a drum robot that can automatically complete music transcription in real-time, which is based on AIoT and fog computing technology. Specifically, this drum robot system consists of a cloud node for data storage, edge nodes for real-time computing, and data-oriented execution application nodes. In order to analyze drumming music and realize drum transcription, we further propose a light-weight convolutional neural network model to classify drums, which can be more effectively deployed in terminal devices for fast edge calculations. The experimental results show that the proposed system can achieve more competitive performance and enjoy a variety of smart applications and services.

Abstract: This paper introduces a novel GPS-aided visual-wheel odometry (GPS-VWO) for ground robots. The state estimation algorithm tightly fuses visual, wheeled encoder and GPS measurements in the way of Multi-State Constraint Kalman Filter (MSCKF). To avoid accumulating calibration errors over time, the proposed algorithm calculates the extrinsic rotation parameter between the GPS global coordinate frame and the VWO reference frame online as part of the estimation process. The convergence of this extrinsic parameter is guaranteed by the observability analysis and verified by using real-world visual and wheel encoder measurements as well as simulated GPS measurements. Moreover, a novel theoretical finding is presented that the variance of unobservable state could converge to zero for specific Kalman filter system. We evaluate the proposed system extensively in large-scale urban driving scenarios. The results demonstrate that better accuracy than GPS is achieved through the fusion of GPS and VWO. The comparison between extrinsic parameter calibration and non-calibration shows significant improvement in localization accuracy thanks to the online calibration.

Abstract: Summarizing knowledge from animals and human beings inspires robotic innovations. In this work, we propose a framework for driving legged robots act like real animals with lifelike agility and strategy in complex environments. Inspired by large pre-trained models witnessed with impressive performance in language and image understanding, we introduce the power of advanced deep generative models to produce motor control signals stimulating legged robots to act like real animals. Unlike conventional controllers and end-to-end RL methods that are task-specific, we propose to pre-train generative models over animal motion datasets to preserve expressive knowledge of animal behavior. The pre-trained model holds sufficient primitive-level knowledge yet is environment-agnostic. It is then reused for a successive stage of learning to align with the environments by traversing a number of challenging obstacles that are rarely considered in previous approaches, including creeping through narrow spaces, jumping over hurdles, freerunning over scattered blocks, etc. Finally, a task-specific controller is trained to solve complex downstream tasks by reusing the knowledge from previous stages. Enriching the knowledge regarding each stage does not affect the usage of other levels of knowledge. This flexible framework offers the possibility of continual knowledge accumulation at different levels. We successfully apply the trained multi-level controllers to the MAX robot, a quadrupedal robot developed in-house, to mimic animals, traverse complex obstacles, and play in a designed challenging multi-agent Chase Tag Game, where lifelike agility and strategy emerge on the robots. The present research pushes the frontier of robot control with new insights on reusing multi-level pre-trained knowledge and solving highly complex downstream tasks in the real world.

Abstract: Dexterous in-hand manipulation is a peculiar and useful human skill. This ability requires the coordination of many senses and hand motion to adhere to many constraints. These constraints vary and can be influenced by the object characteristics or the specific application. One of the key elements for a robotic platform to implement reliable inhand manipulation skills is to be able to integrate those constraints in their motion generations. These constraints can be implicitly modelled, learned through experience or human demonstrations. We propose a method based on motion primitives dictionaries to learn and reproduce in-hand manipulation skills. In particular, we focused on fingertip motions during the manipulation, and we defined an optimization process to combine motion primitives to reach specific fingertip configurations. The results of this work show that the proposed approach can generate manipulation motion coherent with the human one and that manipulation constraints are inherited even without an explicit formalization.

Abstract: Given its increasing popularity in recent years, teleoperation technology is now recognized as a robust fallback solution for Automated Driving (AD). Remote Assistance (RA) represents an event-driven class of teleoperation with a distinct division of tasks between the Autonomous Vehicle (AV) and the remote human operator. This paper presents a novel approach for RA of AVs in urban environments. The concept draws inspiration from the potential synergy between highly-automated systems and human operators to collaboratively solve complex driving situations. Utilizing a hybrid algorithm that makes use of the Operational Design Domain (ODD) modification idea, it considers actions that go beyond the nominal operational space. Combined with the advanced cognitive reasoning of the human remote operator, the concept offers features that hold the potential to significantly improve both RA and AD user experiences.

Abstract: Robotic manipulators are often designed with more actuated degrees-of-freedom than required to fully control an end effector's position and orientation. These "redundant" manipulators can allow infinite joint configurations that satisfy a particular task-space position and orientation, providing more possibilities for the manipulator to traverse a smooth collision-free trajectory. However, finding such a trajectory is non-trivial because the inverse kinematics for redundant manipulators cannot typically be solved analytically. Many strategies have been developed to tackle this problem, including Jacobian pseudo-inverse method, rapidly-expanding-random tree (RRT) motion planning, and quadratic programming (QP) based methods. Here, we present a flexible inverse kinematics-based QP strategy (iKinQP). Because it is independent of robot dynamics, the algorithm is relatively light-weight, and able to run in real-time in step with torque control. Collisions are defined as kinematic trees of elementary geometries, making the algorithm agnostic to the method used to determine what collisions are in the environment. Collisions are treated as hard constraints which guarantees the generation of collision-free trajectories. Trajectory smoothness is accomplished through the QP optimization. Our algorithm was evaluated for computational efficiency, smoothness, and its ability to provide trackable trajectories. It was shown that iKinQP is capable of providing smooth, collision-free trajectories at real-time rates.

Abstract: Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the environment, we think that embedding auxiliary information about focus point into robot learning would enhance efficiency and robustness of the learning process. In this paper, we propose a novel approach to model and emulate the human attention with an approximate prediction model. We then leverage this output and feed it as a structured auxiliary feature map into downstream learning tasks. We validate this idea by learning a prediction model from human-gaze recordings of manual driving in the real world. We test our approach on two learning tasks - object detection and imitation learning. Our experiments demonstrate that the inclusion of predicted human attention leads to improved robustness of the trained models to out-of-distribution samples and faster learning in low-data regime settings. Our work highlights the potential of incorporating structured auxiliary information in representation learning for robotics and opens up new avenues for research in this direction. All code and data are available online.

Abstract: New 3+1D high-resolution radar sensors are gaining importance for 3D object detection in the automotive domain due to their relative affordability and improved detection compared to classic low-resolution radar sensors. One limitation of high-resolution radar sensors, compared to lidar sensors, is the sparsity of the generated point cloud. This sparsity could be partially overcome by accumulating radar point clouds of subsequent time steps. This contribution analyzes limitations of accumulating radar point clouds on the View-of-Delft dataset. By employing different ego-motion estimation approaches, the dataset's inherent constraints, and possible solutions are analyzed. Additionally, a learning-based instance motion estimation approach is deployed to investigate the influence of dynamic motion on the accumulated point cloud for object detection. Experiments document an improved object detection performance by applying an ego-motion estimation and dynamic motion correction approach.

Abstract: Intelligent robots are designed to effectively navigate dynamic and unpredictable environments laden with moving mechanical elements and objects. Such environment-induced dynamics, including moving obstacles, can readily alter the computational demand (e.g., the creation of new tasks) and the structure of workloads (e.g., precedence constraints among tasks) during runtime, thereby adversely affecting overall system performance. This challenge is amplified when multi-task inference is expected on robots operating under stringent resource and real-time constraints. To address such a challenge, we introduce RED, a systematic real-time scheduling approach designed to support multi-task deep neural network workloads in resource-limited robotic systems. It is designed to adaptively manage the Robotic Environmental Dynamics (RED) while adhering to real-time constraints. At the core of RED lies a deadline-based scheduler that employs an intermediate deadline assignment policy, effectively managing to change workloads and asynchronous inference prompted by complex, unpredictable environments. This scheduling framework also facilitates the flexible deployment of MIMONet (multi-input multi-output neural networks), which are commonly utilized in multi-tasking robotic systems to circumvent memory bottlenecks. Building on this scheduling framework, RED recognizes and leverages a unique characteristic of MIMONet: its weight-shared architecture. To further accommodate and exploit this feature, RED devises a novel and effective workload refinement and reconstruction process. This process ensures the scheduling framework's compatibility with MIMONet and maximizes efficiency.