Autonomous Robots最新文献

We present a method for enabling Reinforcement Learning of motor control policies for complex skills such as dexterous manipulation. We posit that a key difficulty for training such policies is the difficulty of exploring the problem state space, as the accessible and useful regions of this space form a complex structure along manifolds of the original high-dimensional state space. This work presents a method to enable and support exploration with Sampling-based Planning. We use a generally applicable non-holonomic Rapidly-exploring Random Trees algorithm and present multiple methods to use the resulting structure to bootstrap model-free Reinforcement Learning. Our method is effective at learning various challenging dexterous motor control skills of higher difficulty than previously shown. In particular, we achieve dexterous in-hand manipulation of complex objects while simultaneously securing the object without the use of passive support surfaces. These policies also transfer effectively to real robots. A number of example videos can also be found on the project website: sbrl.cs.columbia.edu

Programmable matter refers to material that can be programmed to alter its physical properties, including its shape. Such matter can be built as a lattice of attached robotic modules, each seen as an autonomous agent with communication and motion capabilities. Self-reconfiguration consists in changing the initial arrangement of modules to form a desired goal shape, and is known to be a complex problem due to its algorithmic complexity and motion constraints. In this paper, we propose to use a max-flow algorithm as a centralized global planner to determine the concurrent paths to be traversed by modules through a porous structure composed of 3D Catoms meta-modules with the aim of increasing the parallelism of motions, and hence decreasing the self-reconfiguration time. We implement a traffic light system as a distributed asynchronous local planning algorithm to control the motions to avoid collisions. We evaluated our algorithm using VisibleSim simulator on different self-reconfiguration scenarios and compared the performance with an existing fully distributed synchronous self-reconfiguration algorithm for similar structures. The results show that the new method provides a significant gain in self-reconfiguration time and energy efficiency.

To navigate in an environment safely and autonomously, robots must accurately estimate where obstacles are and how they move. Instead of using expensive traditional 3D sensors, we explore the use of a much cheaper, faster, and higher resolution alternative: programmable light curtains. Light curtains are a controllable depth sensor that sense only along a surface that the user selects. We adapt a probabilistic method based on particle filters and occupancy grids to explicitly estimate the position and velocity of 3D points in the scene using partial measurements made by light curtains. The central challenge is to decide where to place the light curtain to accurately perform this task. We propose multiple curtain placement strategies guided by maximizing information gain and verifying predicted object locations. Then, we combine these strategies using an online learning framework. We propose a novel self-supervised reward function that evaluates the accuracy of current velocity estimates using future light curtain placements. We use a multi-armed bandit framework to intelligently switch between placement policies in real time, outperforming fixed policies. We develop a full-stack navigation system that uses position and velocity estimates from light curtains for downstream tasks such as localization, mapping, path-planning, and obstacle avoidance. This work paves the way for controllable light curtains to accurately, efficiently, and purposefully perceive and navigate complex and dynamic environments.

Current practice in simulation and implementation of robot controllers is usually undertaken with guidance from high-level design diagrams and pseudocode. Thus, no rigorous connection between the design and the development of a robot controller is established. This paper presents a framework for designing robotic controllers with support for automatic generation of executable code and automatic property checking. A state-machine based notation, RoboChart, and a tool (RoboTool) that implements the automatic generation of code and mathematical models from the designed controllers are presented. We demonstrate the application of RoboChart and its related tool through a case study of a robot performing an exploration task. The automatically generated code is platform independent and is used in both simulation and two different physical robotic platforms. Properties are formally checked against the mathematical models generated by RoboTool, and further validated in the actual simulations and physical experiments. The tool not only provides engineers with a way of designing robotic controllers formally but also paves the way for correct implementation of robotic systems.

Multi-rotor UAVs suffer from a restricted range and flight duration due to limited battery capacity. Autonomous landing on a 2D moving platform offers the possibility to replenish batteries and offload data, thus increasing the utility of the vehicle. Classical approaches rely on accurate, complex and difficult-to-derive models of the vehicle and the environment. Reinforcement learning (RL) provides an attractive alternative due to its ability to learn a suitable control policy exclusively from data during a training procedure. However, current methods require several hours to train, have limited success rates and depend on hyperparameters that need to be tuned by trial-and-error. We address all these issues in this work. First, we decompose the landing procedure into a sequence of simpler, but similar learning tasks. This is enabled by applying two instances of the same RL based controller trained for 1D motion for controlling the multi-rotor’s movement in both the longitudinal and the lateral directions. Second, we introduce a powerful state space discretization technique that is based on i) kinematic modeling of the moving platform to derive information about the state space topology and ii) structuring the training as a sequential curriculum using transfer learning. Third, we leverage the kinematics model of the moving platform to also derive interpretable hyperparameters for the training process that ensure sufficient maneuverability of the multi-rotor vehicle. The training is performed using the tabular RL method Double Q-Learning. Through extensive simulations we show that the presented method significantly increases the rate of successful landings, while requiring less training time compared to other deep RL approaches. Furthermore, for two comparison scenarios it achieves comparable performance than a cascaded PI controller. Finally, we deploy and demonstrate our algorithm on real hardware. For all evaluation scenarios we provide statistics on the agent’s performance. Source code is openly available at https://github.com/robot-perception-group/rl_multi_rotor_landing.

The requirement for a high number of training episodes has been a major limiting factor for the application of Reinforcement Learning (RL) in robotics. Learning skills directly on real robots requires time, causes wear and tear and can lead to damage to the robot and environment due to unsafe exploratory actions. The success of learning skills in simulation and transferring them to real robots has also been limited by the gap between reality and simulation. This is particularly problematic for tasks involving contact with the environment as contact dynamics are hard to model and simulate. In this paper we propose a framework which leverages a shared control framework for modeling known constraints defined by object interactions and task geometry to reduce the state and action spaces and hence the overall dimensionality of the reinforcement learning problem. The unknown task knowledge and actions are learned by a reinforcement learning agent by conducting exploration in the constrained environment. Using a pouring task and grid-clamp placement task (similar to peg-in-hole) as use cases and a 7-DoF arm, we show that our approach can be used to learn directly on the real robot. The pouring task is learned in only 65 episodes (16 min) and the grid-clamp placement task is learned in 75 episodes (17 min) with strong safety guarantees and simple reward functions, greatly alleviating the need for simulation.

The advent of collaborative robots allows humans and robots to cooperate in a direct and physical way. While this leads to amazing new opportunities to create novel robotics applications, it is challenging to make the collaboration intuitive for the human. From a system’s perspective, understanding the human intentions seems to be one promising way to get there. However, human behavior exhibits large variations between individuals, such as for instance preferences or physical abilities. This paper presents a novel concept for simultaneously learning a model of the human intentions and preferences incrementally during collaboration with a robot. Starting out with a nominal model, the system acquires collaborative skills step-by-step within only very few trials. The concept is based on a combination of model-based reinforcement learning and inverse reinforcement learning, adapted to fit collaborations in which human and robot think and act independently. We test the method and compare it to two baselines: one that imitates the human and one that uses plain maximum entropy inverse reinforcement learning, both in simulation and in a user study with a Franka Emika Panda robot arm.

Localization measurements for an autonomous underwater vehicle (AUV) are often difficult to obtain. In many cases, localization measurements are only available sporadically after the AUV comes to the sea surface. Since the motion of AUVs is often affected by unknown underwater flow fields, the sporadic localization measurements carry information of the underwater flow field. Motion tomography (MT) algorithms have been developed to compute a underwater flow map based on the sporadic localization measurements. This paper extends MT by introducing Laplacian regularization in to the problem formulation and the MT algorithm. Laplacian regularization enforces smoothness in the spatial distribution of the underwater flow field. The resulted Laplacian regularized motion tomography (RMT) algorithm converges to achieve a finite error bounded. The performance of the RMT and other variants of MT are compared through the method of data resolution analysis. The improved performance of RMT is confirmed by experimental data collected from underwater glider ocean sensing experiments.

Robotics researchers have been focusing on developing autonomous and human-like intelligent robots that are able to plan, navigate, manipulate objects, and interact with humans in both static and dynamic environments. These capabilities, however, are usually developed for direct interactions with people in controlled environments, and evaluated primarily in terms of human safety. Consequently, human-robot interaction (HRI) in scenarios with no intervention of technical personnel is under-explored. However, in the future, robots will be deployed in unstructured and unsupervised environments where they will be expected to work unsupervised on tasks which require direct interaction with humans and may not necessarily be collaborative. Developing such robots requires comparing the effectiveness and efficiency of similar design approaches and techniques. Yet, issues regarding the reproducibility of results, comparing different approaches between research groups, and creating challenging milestones to measure performance and development over time make this difficult. Here we discuss the international robotics competition called RoboCup as a benchmark for the progress and open challenges in AI and robotics development. The long term goal of RoboCup is developing a robot soccer team that can win against the world’s best human soccer team by 2050. We selected RoboCup because it requires robots to be able to play with and against humans in unstructured environments, such as uneven fields and natural lighting conditions, and it challenges the known accepted dynamics in HRI. Considering the current state of robotics technology, RoboCup’s goal opens up several open research questions to be addressed by roboticists. In this paper, we (a) summarise the current challenges in robotics by using RoboCup development as an evaluation metric, (b) discuss the state-of-the-art approaches to these challenges and how they currently apply to RoboCup, and (c) present a path for future development in the given areas to meet RoboCup’s goal of having robots play soccer against and with humans by 2050.