Small Number Of Demonstrations Research Articles

Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation

Placing robots outside controlled conditions requires versatile movement representations that allow robots to learn new tasks and adapt them to environmental changes. The introduction of obstacles or the placement of additional robots in the workspace, the modification of the joint range due to faults or range-of-motion constraints are typical cases where the adaptation capabilities play a key role for safely performing the robot's task. Probabilistic movement primitives (ProMPs) have been proposed for representing adaptable movement skills, which are modelled as Gaussian distributions over trajectories. These are analytically tractable and can be learned from a small number of demonstrations. However, both the original ProMP formulation and the subsequent approaches only provide solutions to specific movement adaptation problems, e.g., obstacle avoidance, and a generic, unifying, probabilistic approach to adaptation is missing. In this paper we develop a generic probabilistic framework for adapting ProMPs. We unify previous adaptation techniques, for example, various types of obstacle avoidance, via-points, mutual avoidance, in one single framework and combine them to solve complex robotic problems. Additionally, we derive novel adaptation techniques such as temporally unbound via-points and mutual avoidance. We formulate adaptation as a constrained optimisation problem where we minimise the Kullback-Leibler divergence between the adapted distribution and the distribution of the original primitive while we constrain the probability mass associated with undesired trajectories to be low. We demonstrate our approach on several adaptation problems on simulated planar robot arms and 7-DOF Franka-Emika robots in a dual robot arm setting.

Show Me What You Can Do: Capability Calibration on Reachable Workspace for Human-Robot Collaboration

Aligning humans’ assessment of what a robot can do with its true capability is crucial for establishing a common ground between human and robot partners when they collaborate on a joint task. In this work, we propose an approach to calibrate humans’ estimate of a robot’s reachable workspace through a small number of demonstrations <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">before</i> collaboration. We develop a novel motion planning method, reachability-expressive motion planning (REMP), which jointly optimizes the physical cost and the expressiveness of robot motion to reveal the robot’s reachability to a human observer. Our experiments with human participants demonstrate that a short calibration using REMP can effectively align a non-expert user’s estimation of the robot’s reachability with its true capacity. We show that this calibration procedure not only results in better user perception, but also promotes more efficient human-robot collaborations in a subsequent joint task. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Q-Attention: Enabling Efficient Learning for Vision-Based Robotic Manipulation

Despite the success of reinforcement learning methods, they have yet to have their breakthrough moment when applied to a broad range of robotic manipulation tasks. This is partly due to the fact that reinforcement learning algorithms are notoriously difficult and time consuming to train, which is exacerbated when training from images rather than full-state inputs. As humans perform manipulation tasks, our eyes closely monitor every step of the process with our gaze focusing sequentially on the objects being manipulated. With this in mind, we present our Attention-driven Robotic Manipulation (ARM) algorithm, which is a general manipulation algorithm that can be applied to a range of sparse-rewarded tasks, given only a small number of demonstrations. ARM splits the complex task of manipulation into a 3 stage pipeline: (1) a Q-attention agent extracts relevant pixel locations from RGB and point cloud inputs, (2) a next-best pose agent that accepts crops from the Q-attention agent and outputs poses, and (3) a control agent that takes the goal pose and outputs joint actions. We show that current learning algorithms fail on a range of RLBench tasks, whilst ARM is successful. Videos found at: <uri>https://sites.google.com/view/q-attention</uri>.

Learning Camera Control in Dynamic Scenes from Limited Demonstrations

AbstractIn this work, we present our strategy for camera control in dynamic scenes with multiple people (sports teams). We learn a generic model of the player dynamics offline in simulation. We use only a few sparse demonstrations of a user's camera control policy to learn a reward function to drive camera motion in an ongoing dynamic scene. Key to our approach is the creation of a low‐dimensional representation of the scene dynamics which is independent of the environment action and rewards, which enables learning the reward function using only a small number of examples. We cast the user‐specific control objective as an inverse reinforcement learning problem, aiming to learn an expert's intention from a small number of demonstrations. The learned reward function is used in combination with a visual model predictive controller (MPC). We learn a generic scene dynamics model that is agnostic to the user‐specific reward, enabling reusing the same dynamics model for different camera control policies. We show the effectiveness of our method on simulated and real soccer matches.

Robot complex motion learning based on unsupervised trajectory segmentation and movement primitives

This paper presents a robot skill acquisition framework for learning and reproducing humanoid trajectories with complex forms. A new unsupervised segmentation method is proposed to detect motion units in the demonstrated kinematic data using the concept of key points. To find the consistent features of trajectories, a Hidden Semi-Markov Model (HSMM) is used to identify key points common to all the demonstrations. Generalizing the motion units is achieved via a Probability-based Movement Primitive (PbMP), which encapsulates multiple trajectories into one model. Such a framework can generate trajectories suitable for robot execution with arbitrary shape and complexity from a small number of demonstrations, which greatly expands the application scenarios of robot programming by demonstration. The automatic segmentation process does not rely on a priori knowledge or models for specific tasks, and the generalized trajectory retains more consistent features than those produced by other algorithms. We demonstrate the effectiveness of the proposed framework through simulations and experiments.

Combining Imitation Learning With Constraint-Based Task Specification and Control

This letter combines an combines an imitation learning approach with a model-based and constraint-based task specification and control methodology. Imitation learning provides an intuitive way for the end user to specify context of a new robot application without the need of traditional programming skills. On the other hand, constraint-based robot programming allows us to define complex tasks involving different kinds of sensor input. Combination of both enables adaptation of complex tasks to new environments and new objects with a small number of demonstrations. The proposed method uses a statistical uni-modal model to describe the demonstrations in terms of a number of weighted basis functions. This is then combined with model-based descriptions of other aspects of the task at hand. This approach was tested in a use case inspired by an industrial application, in which the required transfer motions were learned from a small number of demonstrations, and gradually improved by adding new demonstrations. Information on a collision-free path was introduced through a small number of demonstrations. The method showed a high level of composability with force and vision controlled tasks. The use case showed that the deployment of a complex constraint-based task with sensor interactions can be expedited using imitation learning.

From revolution to apathy ? American student activism in the 1970s

The contrast between the widespread activism of the 1960s and the relative calm of the 1970s in the American universities is dramatic. In general, American students are not now politically active, although there have been a small number of demonstrations. The political traditions of American students are important to understand in order to analyze the current situation. The first period of widespread activism was during the 1930s, with the decade of the 1950s returning to political calm. The sixties was the zenith of American student activism, and the impact of the counter culture and of some of the political struggles of this period continues to influence the campus. The lack of a clearly threatening foreign policy issue, economic problems, disillusionment with past politics and other factors have all contributed to the political quiet of the seventies. The paper concludes with a description of current campus trends.