Autonomous Robots最新文献

Training language-conditioned policies is typically time-consuming and resource-intensive. Additionally, the resulting controllers are tailored to the specific robot they were trained on, making it difficult to transfer them to other robots with different dynamics. To address these challenges, we propose a new approach called Hierarchical Modularity, which enables more efficient training and subsequent transfer of such policies across different types of robots. The approach incorporates Supervised Attention which bridges the gap between modular and end-to-end learning by enabling the re-use of functional building blocks. In this contribution, we build upon our previous work, showcasing the extended utilities and improved performance by expanding the hierarchy to include new tasks and introducing an automated pipeline for synthesizing a large quantity of novel objects. We demonstrate the effectiveness of this approach through extensive simulated and real-world robot manipulation experiments.

Task planning systems have been developed to help robots use human knowledge (about actions) to complete long-horizon tasks. Most of them have been developed for “closed worlds” while assuming the robot is provided with complete world knowledge. However, the real world is generally open, and the robots frequently encounter unforeseen situations that can potentially break theplanner’s completeness. Could we leverage the recent advances on pre-trained Large Language Models (LLMs) to enable classical planning systems to deal with novel situations? This paper introduces a novel framework, called COWP, for open-world task planning and situation handling. COWP dynamically augments the robot’s action knowledge, including the preconditions and effects of actions, with task-oriented commonsense knowledge. COWP embraces the openness from LLMs, and is grounded to specific domains via action knowledge. For systematic evaluations, we collected a dataset that includes 1085 execution-time situations. Each situation corresponds to a state instance wherein a robot is potentially unable to complete a task using a solution that normally works. Experimental results show that our approach outperforms competitive baselines from the literature in the success rate of service tasks. Additionally, we have demonstrated COWP using a mobile manipulator. Supplementary materials are available at: https://cowplanning.github.io/

Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks. Our key insight is to prompt the LLM with program-like specifications of the available actions and objects in an environment, as well as with example programs that can be executed. We make concrete recommendations about prompt structure and generation constraints through ablation experiments, demonstrate state of the art success rates in VirtualHome household tasks, and deploy our method on a physical robot arm for tabletop tasks. Website and code at progprompt.github.io

Decentralized multi-robot systems typically perform coordinated motion planning by constantly broadcasting their intentions to avoid collisions. However, the risk of collision between robots varies as they move and communication may not always be needed. This paper presents an efficient communication method that addresses the problem of “when” and “with whom” to communicate in multi-robot collision avoidance scenarios. In this approach, each robot learns to reason about other robots’ states and considers the risk of future collisions before asking for the trajectory plans of other robots. We introduce a new neural architecture for the learned communication policy which allows our method to be scalable. We evaluate and verify the proposed communication strategy in simulation with up to twelve quadrotors, and present results on the zero-shot generalization/robustness capabilities of the policy in different scenarios. We demonstrate that our policy (learned in a simulated environment) can be successfully transferred to real robots.

One of the most important barriers towards a widespread use of mobile robots in unstructured, human populated and possibly a-priori unknown work environments is the ability to plan a safe path. In this paper, we propose to delegate this activity to a human operator that walks in front of the robot marking with her/his footsteps the path to be followed. The implementation of this approach requires a high degree of robustness in locating the specific person to be followed (the path-finder). We propose a three phases approach to fulfil this goal: 1. Identification and tracking of the person in the image space, 2. Sensor fusion between camera data and laser sensors, 3. Point interpolation with continuous curvature paths. The approach is described in the paper and extensively validated with experimental results.

Traversability prediction is a fundamental perception capability for autonomous navigation. Deep neural networks (DNNs) have been widely used to predict traversability during the last decade. The performance of DNNs is significantly boosted by exploiting a large amount of data. However, the diversity of data in different domains imposes significant gaps in the prediction performance. In this work, we make efforts to reduce the gaps by proposing a novel pseudo-trilateral adversarial model that adopts a coarse-to-fine alignment (CALI) to perform unsupervised domain adaptation (UDA). Our aim is to transfer the perception model with high data efficiency, eliminate the prohibitively expensive data labeling, and improve the generalization capability during the adaptation from easy-to-access source domains to various challenging target domains. Existing UDA methods usually adopt a bilateral zero-sum game structure. We prove that our CALI model—a pseudo-trilateral game structure is advantageous over existing bilateral game structures. This proposed work bridges theoretical analyses and algorithm designs, leading to an efficient UDA model with easy and stable training. We further develop a variant of CALI—Informed CALI, which is inspired by the recent success of mixup data augmentation techniques and mixes informative regions based on the results of CALI. This mixture step provides an explicit bridging between the two domains and exposes under-performing classes more during training. We show the superiorities of our proposed models over multiple baselines in several challenging domain adaptation setups. To further validate the effectiveness of our proposed models, we then combine our perception model with a visual planner to build a navigation system and show the high reliability of our model in complex natural environments.

This paper presents the design and control of a high-speed running bipedal robot, BRAVER. The robot, which weighs 8.6 kg and is 0.36 m tall, has six active degrees, all of which are driven by custom back-driveable modular actuators, which enable high-bandwidth force control and proprioceptive torque feedback. We present the details of the hardware design, including the actuator, leg, foot, and onboard control systems, as well as the locomotion controller design for high dynamic tasks and improving robustness. We have demonstrated the performance of BRAVER using a series of experiments, including multi-terrains walking, up and down 15(^{circ }) slopes, pushing recovery, and running. The maximum running speed of BRAVER reaches 1.75 m/s.

There is a large class of real-world problems, such as warehouse transport, at different scales, swarm densities, etc., that can be characterized as Central Place Foraging Problems (CPFPs). We contribute to swarm engineering by designing an Ordinary Differential Equation (ODE) model that strives to capture the underlying behavioral dynamics of the CPFP in these application areas. Our simulation results show that a hybrid ODE modeling approach combining analytic parameter calculations and post-hoc (i.e., after running experiments) parameter fitting can be just as effective as a purely post-hoc approach to computing parameters via simulations, while requiring less tuning and iterative refinement. This makes it easier to design systems with provable bounds on behavior. Additionally, the resulting model parameters are more understandable because their values can be traced back to problem features, such as system size, robot control algorithm, etc. Finally, we perform real-robot experiments to further understand the limits of our model from an engineering standpoint.

Robotics faces a long-standing obstacle in which the speed of the vision system’s scene understanding is insufficient, impeding the robot’s ability to perform agile tasks. Consequently, robots must often rely on interpolation and extrapolation of the vision data to accomplish tasks in a timely and effective manner. One of the primary reasons for these delays is the analog-to-digital conversion that occurs on a per-pixel basis across the image sensor, along with the transfer of pixel-intensity information to the host device. This results in significant delays and power consumption in modern visual processing pipelines. The SCAMP-5—a general-purpose Focal-plane Sensor-processor array (FPSP)—used in this research performs computations in the analog domain prior to analog-to-digital conversion. By extracting features from the image on the focal plane, the amount of data that needs to be digitised and transferred is reduced. This allows for a high frame rate and low energy consumption for the SCAMP-5. The focus of our work is on localising the camera within the scene, which is crucial for scene understanding and for any downstream robotics tasks. We present a localisation system that utilise the FPSP in two parts. First, a 6-DoF odometry system is introduced, which efficiently estimates its position against a known marker at over 400 FPS. Second, our work is extended to implement BIT-VO—6-DoF visual odometry system which operates under an unknown natural environment at 300 FPS.

In this paper, an optimal bounded robust control algorithm for secure autonomous navigation in quadcopter vehicles is proposed. The controller is developed combining two parts; one dedicated to stabilize the closed-loop system and the second one for dealing and estimating external disturbances as well unknown nonlinearities inherent to the real system’s operations. For bounding the energy used by the system during a mission and, without losing its robustness properties, the quadratic problem formulation is used considering the actuators system constraints. The resulting optimal bounded control scheme improves considerably the stability and robustness of the closed-loop system and at the same time bounds the motor control inputs. The controller is validated in real-time flights and in unconventional conditions for high wind-gusts and Loss of Effectiveness in two rotors. The experimental results demonstrate the good performance of the proposed controller in both scenarios.