Prototype real-world RL environment for robotics training.
problem Lack of common real-world RL benchmark.
method Developed OffWorld Gym with open access to real-world robotics environments.
result Baseline results in navigation task on real and simulated terrain.
Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take significant time. In this paper, we focus on learning a realistic world model capturi…
Study benchmarks RL algorithms on real robots, revealing their performance and hyper-parameter sensitivity.
problem Lack of benchmark tasks and source code for reinforcement learning on physical robots.
method Introduced benchmark tasks with multiple robots, tested 4 RL algorithms, analyzed hyper-parameter sensitivity.
result Some RL implementations can be applied to physical robots with proper setup, but hyper-parameters need re-tuning.
This work tackles real-world robotic reinforcement learning challenges.
problem Limited success of reinforcement learning in real-world robotics.
method Proposes a system for autonomous real-world learning without instrumentation.
result Demonstrates a complete system that learns without human intervention.
Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the …
A new framework for robot block-stacking tasks using causal probabilistic models.
problem Robots fail outside controlled environments due to uncertainty and lack of explicit design for all scenarios.
method Causal probabilistic framework combining causal models and probabilistic representations of noise.
result Robots can perceive, reason about, and explain their environment for block-stacking tasks.
RL controls small soccer robots in a real league, beating human-designed policies.
problem Training robots to play complex, real-world sports.
method Sim-to-Real RL approach, training in simulated environment, applying to real-world robots.
result Robots learned policies to compete effectively, beating human-designed strategies.
Deep RL learns robot walking gaits in real-world environments.
problem Difficulty in applying deep RL to real-world robotic tasks due to poor sample complexity and hyperparameter sensitivity.
method Sample-efficient deep RL algorithm based on maximum entropy RL, requiring minimal per-task tuning and modest trials.
result Acquired stable walking gaits on a real-world Minitaur robot in about two hours.
Robots navigate wilderness trails using virtual-to-real-world transfer learning.
problem Autonomous navigation of outdoor trails is challenging due to lack of annotated training data.
method Virtual-to-real-world transfer learning with deep learning models trained on synthetic data.
result Classification accuracies of up to 95% on synthetic data and feasibility in real-world trails.
Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world ro…
Robot learns to juggle two balls from 56 minutes of experience.
problem Learning high-acceleration tasks in the real-world with binary rewards.
method Designs a learning system that incorporates safety and sample efficiency.
result High-speed manipulator learns to juggle for up to 33 minutes.
Robotic learning without reward engineering from images.
problem Manual reward engineering for reinforcement learning in robotics.
method Learning from examples and active solicitation of labels.
result Efficient learning of robotic skills from images without manual rewards.
This work evaluates task-agnostic exploration methods for fixed-batch learning.
problem Expensive real-world experience for robotics tasks.
method Fixed datasets for arbitrary task learning.
result Improved offline learning for robotics tasks.
Hybrid RL combines simulated and real data for robust autonomous flight.
problem Challenges in training deep RL models for real-world robotic tasks.
method Combines real-world and simulated data to improve generalization.
result Quadrotor avoids collisions using only a monocular camera.
Efficient attacks on DRL models without model access and low computation.
problem Vulnerabilities of DRL models to adversarial attacks.
method Adapting black-box attacks, introducing efficient online sequential attacks, exploring perturbations in environment dynamics, and generating robust physical perturbations.
result Demonstrated the effectiveness of proposed attacks on real-world robots.
Robot learns to control itself without rewards.
problem Autonomous reinforcement learning without access to rewards.
method Distributional planning networks optimizing for an embedding space.
result Learned goal metrics enable autonomous reinforcement learning.
For a safe, natural and effective human-robot social interaction, it is essential to develop a system that allows a robot to demonstrate the perceivable responsive behaviors to complex human behaviors. We introduce the Multimodal Deep Attention Recurrent Q-Network using which the robot exhibits human-like social intera…
New method improves smoothness of robot learning.
problem Jerky motion patterns on real robots from Deep RL exploration.
method Adapting state-dependent exploration to Deep RL algorithms with gSDE.
result Improved exploration and performance on real robots.
Survey examines challenges and solutions in sim-to-real transfer for robotics.
problem Challenges in transferring robotic systems from simulation to real-world environments.
method Leveraging techniques like domain randomization, real-to-sim transfer, state and action abstractions, and sim-real co-training.
result Promising results in closing the reality gap across various robotic domains.
Robotic arm learns to manipulate a ball by choosing goals from learned experience.
problem Efficient discovery of skills for long-living autonomous agents without supervision.
method Intrinsically motivated goal exploration using learned goal spaces from deep representation learning.
result Recent results show applicability of learned goal spaces on real-world robotic tasks.
Automates decision-making for human operators managing multiple robots.
problem Limited human operator attention when controlling multiple robots.
method Learned model of user preferences from easy settings to automatically identify the most critical robot.
result Automated decision-making can assist human operators in managing more robots than their attention allows.
ROBEL platform accelerates reinforcement learning with low-cost robots.
problem Accelerating reinforcement learning research in robotics.
method Open-source platform of cost-effective robots for real-world reinforcement learning.
result Robots D'Claw and D'Kitty facilitate learning dexterous manipulation and agile locomotion tasks.
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.
Method trains vision and control policies on real robots quickly.
problem Training vision-based control policies on real robots efficiently.
method Multi-task Reinforcement Learning with auxiliary tasks.
result Significant learning speed-ups and task learning from-scratch.
Robots learn to navigate rough terrain using reinforcement learning.
problem Generalizing robot behavior to new, unseen rough terrains.
method PPMC RL Training Algorithm
result Robots achieve 100% success rate in learning new rough terrain maps.
Robot learns from human demonstrations to work autonomously.
problem Leveraging human and robotic strengths in human-robot systems.
method Bayesian inference for detecting and classifying human heterogeneity.
result Bayesian approach outperforms conventional methods by up to 12.8. This work shows how to use simulators to learn efficient exploration in real-world RL.
problem Sample complexity of real-world reinforcement learning.
method Coupling exploratory policies learned in simulators with practical approaches.
result Polynomial sample complexity in real world, exponential improvement over direct sim2real transfer.
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…
Central to robot exploration and mapping is the task of persistent localization in environmental fields characterized by spatially correlated measurements. This paper presents a Gaussian process localization (GP-Localize) algorithm that, in contrast to existing works, can exploit the spatially correlated field measurem…
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.
Survey on RL reproducibility using real-world robots.
problem Difficulty in reproducing RL results due to algorithm variance, environment stochasticity, and hyper-parameters.
method Investigates issues leading to irreproducible RL research and standardizes evaluation approach.
result Shows how to manage and standardize evaluation of RL algorithms for unbiased comparison.
Paper proposes an end-to-end learning method for state estimation in robotics.
problem Lack of annotated data for optimising dynamic and measurement models in particle filters.
method End-to-end learning objective based on maximising a pseudo-likelihood function.
result Improves state estimation when large portions of true states are unknown.
SAC improves deep RL by balancing reward and randomness.
problem High sample complexity and hyperparameter brittleness in RL.
method Maximum entropy framework, constrained optimization, temperature tuning.
result SAC achieves state-of-the-art performance and stability.
Applications of safety, security, and rescue in robotics, such as multi-robot target tracking, involve the execution of information acquisition tasks by teams of mobile robots. However, in failure-prone or adversarial environments, robots get attacked, their communication channels get jammed, and their sensors may fail…
This work tackles autonomous learning of interrelated tasks in robots.
problem Learning interrelated tasks in robots, especially in complex environments.
method Using a multi-task reinforcement learning approach within an MDP framework.
result Demonstrates how to autonomously learn interrelated tasks in robots.
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.
Paper learns domain randomization distributions for robust robot policies.
problem Finding good domain randomization parameters for simulation without real data.
method Gradient-based search methods to learn domain randomization distribution.
result Improvements in jump-start and asymptotic performance when transferring policies.
RHPO improves data-efficiency for hierarchical reinforcement learning.
problem High data requirements for general reinforcement learning algorithms in robotics.
method RHPO employs compositional inductive biases and task sharing mechanisms.
result RHPO enables stable and fast learning for complex domains with positive transfer.
Proposes KStar Diffuser for kinematics-aware bimanual robotic manipulation.
problem Challenges in applying imitation learning to bimanual robotic tasks.
method Integrates physical robot structure into action prediction using a dynamic spatial-temporal graph and differentiable kinematics.
result Effective generation of kinematics-aware actions in both simulation and real-world environments.
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.
New framework learns robot tasks quickly from simplified simulations.
problem Long training times and variable-length inputs in RL.
method Combines deep sets encoding with modular RL.
result Effective policies learned in minutes from simplified simulations.
TIDBD adapts step sizes online for better robotic predictions.
problem Choosing appropriate learning parameters for online prediction-learning.
method Temporal-Difference Incremental Delta-Bar-Delta (TIDBD) for step-size adaptation.
result TIDBD performs comparably to classic TD learning and detects sensor failures.
Optimizes machine learning and system identification for real-world physical systems.
problem Estimating parameters in complex, real-world physical systems.
method Combines classical system identification and modern machine learning techniques using optimization-based approaches.
result Developed regularization strategies to incorporate prior knowledge into flexible models.
Robot-assisted dressing offers an opportunity to benefit the lives of many people with disabilities, such as some older adults. However, robots currently lack common sense about the physical implications of their actions on people. The physical implications of dressing are complicated by non-rigid garments, which can r…
A new model for simulating cloth manipulation in robots, accurate to within 1cm.
problem Accurately simulating cloth manipulation in robots, especially in moderate stress environments.
method A continuous, isometric strain model for textiles, treating them as inextensible surfaces with only isometric motions. Aerodynamic effects are incorporated through virtual uncoupling of mass.
result Simulations are accurate to within 1cm compared to real-world manipulation, even with coarse meshes.
Paper presents a method for efficient robot adaptation using fine-tuning.
problem Continuous adaptation of robot learning systems in real-world scenarios.
method Fine-tuning previously learned policies using off-policy reinforcement learning.
result Fine-tuning leads to substantial performance gains and adaptation to new conditions.
Enhances neural rendering with geometry-aware attention.
problem Efficiently modeling complex 3D scenes.
method Introduces Epipolar Cross Attention (ECA) for non-local operations.
result Significant improvement in Generative Query Networks (GQN) performance.
Paper proposes a method to improve off-policy reinforcement learning in batch settings.
problem Challenges in applying off-policy reinforcement learning to batch data.
method Uses a learned prior, the advantage-weighted behavior model (ABM), to bias RL policies.
result Improves performance on various RL tasks, including robot control.