Robust optimization and statistical robustness improve robot navigation policies.
problem Efficiently finding optimal robot navigation policies in uncertain environments.
method Combining robust optimization and statistical robustness with improved Bayesian optimization techniques.
result Safe and repeatable robot navigation policies are achieved with improved robust optimization methods.
E-ROBOT improves robust statistics and ML via Schrödinger bridge theory.
problem Statistical and machine learning tasks in high dimensions.
method Entropic-regularized Robust Optimal Transport (E-ROBOT) framework.
result E-ROBOT avoids the curse of dimensionality with O(n−1/2) sample complexity. Deep RL trains a robust humanoid push-recovery policy.
problem Training robust humanoid push-recovery policies.
method Model-free Deep Reinforcement Learning.
result Policy learns robust behaviors across the entire body.
A new optimizer d-AmsGrad improves deep learning for robot learning in non-stationary problems.
problem Noise and outliers in real-world data make deep learning challenging for robot learning.
method Proposed an improved version of AmsGrad optimizer that slowly decays the maximum second momentum to adapt to non-stationary problems.
result The new optimizer outperformed baseline optimizers in robotics problems.
Robots learn to handle complex tasks creatively using DRL.
problem Robotic manipulation challenges and intelligence.
method Designing challenging manipulation tasks, applying DRL for robot training.
result Robots exhibit creative and non-intuitive problem-solving.
Robots adapt to damage with a single policy and diagnosis.
problem Robotic failure due to damage during mission-critical tasks.
method Damage-aware control architecture using supervised learning for diagnosis and policy adaptation.
result Single-shot diagnosis and adaptation achieved with a single policy.
We propose a principled algorithm for robust Bayesian filtering and smoothing in nonlinear stochastic dynamic systems when both the transition function and the measurement function are described by non-parametric Gaussian process (GP) models. GPs are gaining increasing importance in signal processing, machine learning,…
ROBEL is an open-source platform of cost-effective robots designed for reinforcement learning in the real world. ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a three-fingered hand robot that facilitates learning dexterous manipulation tasks, …
Interest in derivative-free optimization (DFO) and "evolutionary strategies" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics. However, it is well known that DFO methods suffer from proh…
Assistive robots can potentially improve the quality of life and personal independence of elderly people by supporting everyday life activities. To guarantee a safe and intuitive interaction between human and robot, human intentions need to be recognized automatically. As humans communicate their intentions multimodall…
This work analyzes how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems.
problem Collaborative learning in distributed multi-robot systems with varying sensors and actuators.
method Simulation-based analysis using PPO and Bullet physics engine, considering different types of perturbations.
result PPO's robustness is affected by the presence of different types of perturbations and the number of agents experiencing them.
Paper introduces timing-based adversarial attacks on DRL-based navigation systems.
problem Vulnerability of DRL-based navigation systems to adversarial attacks.
method Timing-based adversarial strategies using physical noise patterns.
result Adversarial timing attacks significantly degrade DRL-based navigation performance.
Diffusion models enhance robotic manipulation through probabilistic multi-modal learning.
problem Enhancing robotic manipulation through robust and multi-modal learning.
method Probabilistic diffusion models integrating imitation and reinforcement learning.
result Diffusion models improve grasp learning, trajectory planning, and data augmentation in robotics.
Robotic weed control has seen increased research of late with its potential for boosting productivity in agriculture. Majority of works focus on developing robotics for croplands, ignoring the weed management problems facing rangeland stock farmers. Perhaps the greatest obstacle to widespread uptake of robotic weed con…
This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.
problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.
DistGP models multi-robot mapping with distributed Gaussian process learning.
problem Collaborative mapping by multiple robots with limited local data.
method Sparse Gaussian process with factorisation and distributed training via GBP.
result DistGP achieves superior accuracy and robustness compared to DiNNO.
This research introduces an autonomous robot navigation method using reinforcement learning.
problem Improving robot navigation in complex environments.
method Deep Q Network (DQN) and Proximal Policy Optimization (PPO) models for path planning and decision-making.
result The models enhance robot navigation ability and adaptive learning in unknown environments.
This paper bridges outlier-robust estimation in robotics and computer vision with robust statistics.
problem Outlier-robust estimation for geometric perception in robotics and computer vision.
method Adapting and extending robust linear regression and list-decodable regression to non-convex domains and vector-valued measurements.
result Performance guarantees for modern estimation algorithms in the presence of outliers.
A decentralized deep RL controller improves hexapod locomotion learning.
problem Deep RL struggles with real-world legged robot control.
method Decentralized deep RL on a hexapod robot.
result Decentralized approach learns better and faster.
Learning algorithms are enabling robots to solve increasingly challenging real-world tasks. These approaches often rely on demonstrations and reproduce the behavior shown. Unexpected changes in the environment may require using different behaviors to achieve the same effect, for instance to reach and grasp an object in…
GRAM enhances deep RL for reliable real-world deployment.
problem Generalizing deep RL across in-distribution and out-of-distribution scenarios.
method Introduces a robust adaptation module and a joint training pipeline.
result GRAM achieves strong generalization performance in simulations and hardware.
Mathematical framework for cooperative communication explains belief transmission.
problem Lack of understanding why cooperation enables effective belief transmission.
method Connection to optimal transport theory, deriving prior models, statistical interpretations, proofs of robustness and instability.
result Cooperative communication provably enables effective, robust belief transmission.
Paper learns versatile balancing and recovery motions for humanoid robots.
problem Training humanoid robots to handle unexpected perturbations.
method Hierarchical Deep Reinforcement Learning in a physics simulator.
result Learned skills comparable to preprogrammed controllers but more adaptable.
The paper develops a method to create robust control policies for robots using information bottlenecks.
problem Robotic control policies are sensitive to task-irrelevant state and sensor changes.
method Derives a policy gradient algorithm that creates an information bottleneck between states and task-relevant representations.
result Task-driven policies are more robust to sensor noise and environmental changes.
Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, …
Predictions and predictive knowledge have seen recent success in improving not only robot control but also other applications ranging from industrial process control to rehabilitation. A property that makes these predictive approaches well suited for robotics is that they can be learned online and incrementally through…
Mitigates instability in reinforcement learning for safer robotics.
problem Unstable training dynamics in reinforcement learning, especially for safety-sensitive tasks.
method Maintains a history of the agent and reverts to previous parameters when performance decreases.
result Improves performance and stability compared to state-of-the-art algorithms.
Bayesian optimization adapts domain parameters for more robust robot policies.
problem Learning policies for robot control from simulation data often fails in the real world due to the 'reality gap'.
method Bayesian Domain Randomization (BayRn) uses Bayesian optimization to adapt domain parameter distributions during training.
result BayRn achieves better sim-to-real transfer compared to fixed distribution methods.
SCPO learns robust policies without modeling disturbance, improving real-world task performance.
problem Poor performance of reinforcement learning in real-world tasks due to disturbance in transition dynamics.
method State-conservative policy optimization (SCPO) that reduces disturbance to state space and approximates it with a gradient-based regularizer.
result SCPO learns robust policies without prior knowledge of disturbance or simulators, improving performance in robot control tasks.
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
This paper improves robot traders' market impact sensitivity.
problem Market impact in automated trading systems.
method Critiqued existing methods, introduced MLOFI, and demonstrated new algorithms.
result New imbalance-sensitive trader-agents exhibit market impact effects.
Machine vision is critical to robotics due to a wide range of applications which rely on input from visual sensors such as autonomous mobile robots and smart production systems. To create the smart homes and systems of tomorrow, an overview about current challenges in the research field would be of use to identify furt…
The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. Among the few proposed approaches, the recent…
Probabilistic representations of movement primitives open important new possibilities for machine learning in robotics. These representations are able to capture the variability of the demonstrations from a teacher as a probability distribution over trajectories, providing a sensible region of exploration and the abili…
Mobile robot navigation in complex and dynamic environments is a challenging but important problem. Reinforcement learning approaches fail to solve these tasks efficiently due to reward sparsities, temporal complexities and high-dimensionality of sensorimotor spaces which are inherent in such problems. We present a nov…
A new method speeds up uncertainty estimation in image classification.
problem Fast and accurate uncertainty estimation for robust robotics applications.
method Deep sub-ensembles, where only layers close to the output are ensembled.
result Significant speedup in uncertainty estimation with minimal error and NLL increase.
Deep reinforcement learning (deep RL) holds the promise of automating the acquisition of complex controllers that can map sensory inputs directly to low-level actions. In the domain of robotic locomotion, deep RL could enable learning locomotion skills with minimal engineering and without an explicit model of the robot…
Robust reinforcement learning agents generalize well to out-of-distribution settings using pretrained representations.
problem Achieving sample-efficient reinforcement learning agents that generalize to real-world settings.
method Trained 240 representations and 10,000 RL policies on a simulated robotic setup, evaluating different pretrained VAE-based representations' effects on OOD generalization.
result Many reinforcement learning agents are surprisingly robust to realistic distribution shifts, including sim-to-real cases.
CVRL tackles complex visual observations in reinforcement learning.
problem Complex visual observations in natural environments.
method Contrastive Variational Reinforcement Learning (CVRL) learns a contrastive variational model by maximizing mutual information between latent states and observations.
result CVRL achieves comparable performance with state-of-the-art model-based DRL methods and significantly outperforms them on tasks with complex observations.
Introduces GFC for learning complex dynamical systems with geometric constraints.
problem Challenges in accurately modeling and predicting complex dynamical systems with geometric constraints.
method Geometric Contact Flows (GFC) using Riemannian and Contact geometry as inductive biases.
result Ensemble of contactomorphisms adapt the latent contact Hamiltonian model to target dynamics while preserving desirable properties.
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of…
We propose Generative Predecessor Models for Imitation Learning (GPRIL), a novel imitation learning algorithm that matches the state-action distribution to the distribution observed in expert demonstrations, using generative models to reason probabilistically about alternative histories of demonstrated states. We show …
This work uses QPGPs to improve ILC performance in repetitive tasks.
problem Performance degradation in repetitive motion tasks due to environmental changes and robot wear.
method Incorporates Quasi-Periodic Gaussian Processes into a predictive ILC framework.
result The proposed approach achieves faster convergence and robustness under disturbances.
Model learns and plans in real-time under constraints for robotic systems.
problem Challenges in applying reinforcement learning to robotic systems, especially handling continuous state and action spaces, time/resource budget, and hard constraints.
method Combines Gaussian Process regression and Receding Horizon Control. Uses sparse spectrum Gaussian Processes for incremental model updates from sensory data.
result Demonstrates benefits of online learning on autonomous racing tasks and reusability of learned dynamics.
Active localization is the problem of generating robot actions that allow it to maximally disambiguate its pose within a reference map. Traditional approaches to this use an information-theoretic criterion for action selection and hand-crafted perceptual models. In this work we propose an end-to-end differentiable meth…
Recent studies show that Deep Reinforcement Learning (DRL) models are vulnerable to adversarial attacks, which attack DRL models by adding small perturbations to the observations. However, some attacks assume full availability of the victim model, and some require a huge amount of computation, making them less feasible…
SLAM-net learns to navigate visually in challenging indoor environments.
problem Challenges in SLAM for visual robot navigation, especially in noisy conditions.
method Differentiable SLAM Network (SLAM-net) that encodes a particle filter SLAM algorithm in a differentiable graph and learns components through backpropagation.
result Significantly outperforms ORB-SLAM in noisy conditions and improves the Habitat Challenge 2020 PointNav task.
Autonomous robots often encounter challenging situations where their control policies fail and an expert human operator must briefly intervene, e.g., through teleoperation. In settings where multiple robots act in separate environments, a single human operator can manage a fleet of robots by identifying and teleoperati…