Achieving controlled jumping behaviour for a quadruped robot is a challenging task, especially when introducing passive compliance in mechanical design. This study addresses this challenge via imitation-based deep reinforcement learning with a progressive training process. To start, we learn the jumping skill by mimicking a coarse jumping example generated by model-based trajectory optimization. Subsequently, we generalize the learned policy to broader situations, including various distances in both forward and lateral directions, and then pursue robust jumping in unknown ground unevenness. In addition, without tuning the reward much, we learn the jumping policy for a quadruped with parallel elasticity. Results show that using the proposed method, i) the robot learns versatile jumps by learning only from a single demonstration, ii) the robot with parallel compliance reduces the landing error by 11.1%, saves energy cost by 15.2% and reduces the peak torque by 15.8%, compared to the rigid robot without parallel elasticity, iii) the robot can perform jumps of variable distances with robustness against ground unevenness (maximal 4cm height perturbations) using only proprioceptive perception.

To increase the reliability of collaborative robots in performing daily tasks, we require them to be accurate and not only repeatable. However, having a calibrated kinematics model is regrettably a luxury, as available calibration tools are usually more expensive than the robots themselves. With this work, we aim to contribute to the democratization of cobots calibration by providing an inexpensive yet highly effective alternative to existing tools. The proposed minimalist calibration routine relies on a 3D-printable tool as the only physical aid to the calibration process. This two-socket spherical-joint tool kinematically constrains the robot at the end effector while collecting the training set. An optimization routine updates the nominal model to ensure a consistent prediction for each socket and the undistorted mean distance between them. We validated the algorithm on three robotic platforms: Franka, Kuka, and Kinova Cobots. The calibrated models reduce the mean absolute error from the order of 10 mm to 0.2 mm for both Franka and Kuka robots. We provide two additional experimental campaigns with the Franka Robot to render the improvements more tangible. First, we implement Cartesian control with and without the calibrated model and use it to perform a standard peg-in-the-hole task with a tolerance of 0.4 mm between the peg and the hole. Second, we perform a repeated drawing task combining Cartesian control with learning from demonstration. Both tasks consistently failed when the model was not calibrated, while they consistently succeeded after calibration.

Hessian Center for Artificial Intelligence (Hessian.ai), This paper introduces a new imitation learning framework based on energy-based generative models capable of learning complex, physics-dependent, robot motion policies through state-only expert motion trajectories. Our algorithm, called Noise-conditioned Energy-based Annealed Rewards (NEAR), constructs several perturbed versions of the expert's motion data distribution and learns smooth, and well-defined representations of the data distribution's energy function using denoising score matching. We propose to use these learnt energy functions as reward functions to learn imitation policies via reinforcement learning. We also present a strategy to gradually switch between the learnt energy functions, ensuring that the learnt rewards are always well-defined in the manifold of policy-generated samples. We evaluate our algorithm on complex humanoid tasks such as locomotion and martial arts and compare it with state-only adversarial imitation learning algorithms like Adversarial Motion Priors (AMP). Our framework sidesteps the optimisation challenges of adversarial imitation learning techniques and produces results comparable to AMP in several quantitative metrics across multiple imitation settings. Learning skills through imitation is probably the most cardinal form of learning for human beings. Whether it is a child learning to tie their shoelaces, a dancer learning a new pose, or a gymnast learning a fast and complex manoeuvre, acquiring new motor skills for humans typically involves guidance from another skilled human in the form of demonstrations. Acquiring skills from these demonstrations typically boils down to interpreting the individual features of the demonstration motion - for example, the relative positions of the limbs in a dance pose - and subsequently attempting to recreate the same features via repeated trial and error. Imitation learning (IL) is an algorithmic interpretation of this simple strategy of learning skills by matching the features of one's own motions with the features of the expert's demonstrations. Such a problem can be solved by various means, with techniques like behavioural cloning (BC), inverse reinforcement learning (IRL), and their variants being popular choices (Osa et al., 2018). The imitation learning problem can also be formulated in various subtly differing ways, leading to different constraints on the types of algorithms that solve the problem.

Behavior cloning (BC) traditionally relies on demonstration data, assuming the demonstrated actions are optimal. This can lead to overfitting under noisy data, particularly when expressive models are used (e.g., the energy-based model in Implicit BC). To address this, we extend behavior cloning into an iterative process of optimal action estimation within the Interactive Imitation Learning framework. Specifically, we introduce Contrastive policy Learning from Interactive Corrections (CLIC). CLIC leverages human corrections to estimate a set of desired actions and optimizes the policy to select actions from this set. We provide theoretical guarantees for the convergence of the desired action set to optimal actions in both single and multiple optimal action cases. Extensive simulation and real-robot experiments validate CLIC's advantages over existing state-of-the-art methods, including stable training of energy-based models, robustness to feedback noise, and adaptability to diverse feedback types beyond demonstrations. Our code will be publicly available soon.

Real-world environments require robots to continuously acquire new skills while retaining previously learned abilities, all without the need for clearly defined task boundaries. Storing all past data to prevent forgetting is impractical due to storage and privacy concerns. To address this, we propose a method that efficiently restores a robot's proficiency in previously learned tasks over its lifespan. Using an Episodic Memory (EM), our approach enables experience replay during training and retrieval during testing for local fine-tuning, allowing rapid adaptation to previously encountered problems. Additionally, we introduce a selective weighting mechanism that emphasizes the most challenging segments of retrieved demonstrations, focusing local adaptation where it is most needed. This framework offers a scalable solution for lifelong learning without explicit task identifiers or implicit task boundaries, combining retrieval-based adaptation with selective weighting to enhance robot performance in open-ended scenarios. Our approach addresses the challenge of lifelong learning without distinct task boundaries. To emulate human learning patterns, we propose a method consisting of three phases: learning, reviewing, and testing. In the learning phase, the robot is exposed to various demonstrations, storing a subset of this data as episodic memory M. This balance between stability and plasticity is crucial as models face sequences of tasks over time.

Soft robots have the potential to revolutionize the use of robotic systems with their capability of establishing safe, robust, and adaptable interactions with their environment, but their precise control remains challenging. In contrast, traditional rigid robots offer high accuracy and repeatability but lack the flexibility of soft robots. We argue that combining these characteristics in a hybrid robotic platform can significantly enhance overall capabilities. This work presents a novel hybrid robotic platform that integrates a rigid manipulator with a fully developed soft arm. This system is equipped with the intelligence necessary to perform flexible and generalizable tasks through imitation learning autonomously. The physical softness and machine learning enable our platform to achieve highly generalizable skills, while the rigid components ensure precision and repeatability.

Reinforcement learning-based quadruped robots excel across various terrains but still lack the ability to swim in water due to the complex underwater environment. This paper presents the development and evaluation of a data-driven hydrodynamic model for amphibious quadruped robots, aiming to enhance their adaptive capabilities in complex and dynamic underwater environments. The proposed model leverages Neural Ordinary Differential Equations (ODEs) combined with attention mechanisms to accurately process and interpret real-time sensor data. The model enables the quadruped robots to understand and predict complex environmental patterns, facilitating robust decision-making strategies. We harness real-time sensor data, capturing various environmental and internal state parameters to train and evaluate our model. A significant focus of our evaluation involves testing the quadruped robot's performance across different hydrodynamic conditions and assessing its capabilities at varying speeds and fluid dynamic conditions. The outcomes suggest that the model can effectively learn and adapt to varying conditions, enabling the prediction of force states and enhancing autonomous robotic behaviors in various practical scenarios.

Learning from demonstration is a promising way of teaching robots new skills. However, a central problem when executing acquired skills is to recognize risks and failures. This is essential since the demonstrations usually cover only a few mostly successful cases. Inevitable errors during execution require specific reactions that were not apparent in the demonstrations. In this paper, we focus on teaching the robot situational awareness from an initial skill demonstration via kinesthetic teaching and sparse labeling of autonomous skill executions as safe or risky. At runtime, our system, called ILeSiA, detects risks based on the perceived camera images by encoding the images into a low-dimensional latent space representation and training a classifier based on the encoding and the provided labels. In this way, ILeSiA boosts the confidence and safety with which robotic skills can be executed. Our experiments demonstrate that classifiers, trained with only a small amount of user-provided data, can successfully detect numerous risks. The system is flexible because the risk cases are defined by labeling data. This also means that labels can be added as soon as risks are identified by a human supervisor. We provide all code and data required to reproduce our experiments at imitrob.ciirc.cvut.cz/publications/ilesia.

For an autonomous vehicle to operate reliably within real-world traffic scenarios, it is imperative to assess the repercussions of its prospective actions by anticipating the uncertain intentions exhibited by other participants in the traffic environment. Driven by the pronounced multi-modal nature of human driving behavior, this paper presents an approach that leverages Bayesian beliefs over the distribution of potential policies of other road users to construct a novel risk-aware probabilistic motion planning framework. In particular, we propose a novel contingency planner that outputs long-term contingent plans conditioned on multiple possible intents for other actors in the traffic scene. The Bayesian belief is incorporated into the optimization cost function to influence the behavior of the short-term plan based on the likelihood of other agents' policies. Furthermore, a probabilistic risk metric is employed to fine-tune the balance between efficiency and robustness. Through a series of closed-loop safety-critical simulated traffic scenarios shared with human-driven vehicles, we demonstrate the practical efficacy of our proposed approach that can handle multi-vehicle scenarios.

Learning from Interactive Demonstrations has revolutionized the way non-expert humans teach robots. It is enough to kinesthetically move the robot around to teach pick-and-place, dressing, or cleaning policies. However, the main challenge is correctly generalizing to novel situations, e.g., different surfaces to clean or different arm postures to dress. This article proposes a novel task parameterization and generalization to transport the original robot policy, i.e., position, velocity, orientation, and stiffness. Unlike the state of the art, only a set of points are tracked during the demonstration and the execution, e.g., a point cloud of the surface to clean. We then propose to fit a non-linear transformation that would deform the space and then the original policy using the paired source and target point sets. The use of function approximators like Gaussian Processes allows us to generalize, or transport, the policy from every space location while estimating the uncertainty of the resulting policy due to the limited points in the task parameterization point set and the reduced number of demonstrations. We compare the algorithm's performance with state-of-the-art task parameterization alternatives and analyze the effect of different function approximators. We also validated the algorithm on robot manipulation tasks, i.e., different posture arm dressing, different location product reshelving, and different shape surface cleaning.