Safe reinforcement learning for robots using model predictive shielding.
problem Ensuring safety of learned policies in robotics tasks.
method Model Predictive Shielding (MPS) that switches between learned and backup policies.
result Guaranteed safety of learned policies in challenging robotics tasks.
Bayesian Optimization verifies robot controllers against safety violations.
problem Ensuring safety of complex robot controllers in real-world applications.
method Bayesian Optimization framework to test and verify safety constraints.
result The method can find adversarial examples quickly and verify complex safety specifications.
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.
Meta-learning priors improves safe Bayesian optimization.
problem Optimizing robot controllers under safety constraints.
method Meta-learning priors from offline data using F-PACOH.
result Meta-learned priors accelerate safe BO convergence.
DeepMoTIon mimics human navigation in crowds for safe robot movement.
problem Safe navigation of robots in human environments.
method Trains a neural network on pedestrian data to predict human velocity and navigate safely.
result DeepMoTIon outperforms other methods in human imitation and safety compliance.
Bayesian uncertainty from deep learning improves robot safety in unknown areas.
problem Improving robot safety in unknown or dangerous environments.
method Bayesian approximations of uncertainty from deep learning in a robot planner.
result Incorporating uncertainty leads to 18% less risky paths.
SAVED safely learns robot tasks with sparse rewards.
problem Challenges in reinforcement learning for robotics, especially sparse rewards and complex constraints.
method SAVED uses supervision to constrain exploration and learn efficiently, handling complex constraints.
result SAVED outperforms state-of-the-art methods in success rate, constraint satisfaction, and sample efficiency.
A novel controller for wheeled robots handles joystick inputs for smooth steering.
problem Steering control for differential-drive wheeled robots from indirect joystick inputs.
method Developed a geometric controller based on Darboux frame kinematics.
result Smooth trajectories achieved with safety constraints and no desired states.
Study evaluates robot-vision deep learning safety, proposing countermeasures.
problem Vulnerability of robot-vision systems to adversarial examples.
method Empirical analysis and computationally efficient countermeasure.
result Deep networks violate smoothness assumption, making them vulnerable to adversarial examples.
Research tackles safety of deep learning in safety-critical tasks.
problem Safety concerns of deep learning in perception tasks for autonomous agents.
method Technical enumeration and discussions on safety concerns and mitigation methods.
result Need for more mitigation methods to ensure safety of deep learning.
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.
Safe learning of stochastic dynamics with safety constraints.
problem Learning controlled stochastic dynamics with safety constraints.
method Iterative expansion of a safe control set using kernel-based confidence bounds.
result The method ensures safe exploration and efficient estimation of system dynamics.
Paper introduces OTR for efficient offline RL in surgical robotics.
problem Lack of annotated datasets for offline RL in surgical robotics.
method OTR algorithm using Optimal Transport to assign rewards to unlabeled trajectories.
result OTR enables efficient policy learning from large datasets without handcrafted rewards.
Develops a method to simulate rare dangerous events in autonomous systems.
problem Rare dangerous events in safety-critical systems are hard to test in real-world settings.
method Combines exploration, exploitation, and optimization techniques for rare-event simulation.
result Provides rigorous guarantees for the performance of the method.
Automated testing framework finds weaknesses in deep control policies.
problem Safety of deep neural network control policies is difficult to validate.
method Adversarial reinforcement learning to test and find weaknesses.
result Framework finds weaknesses not evident during manual testing.
CARL safely adapts RL agents for safety-critical tasks.
problem Safety hazards in RL for safety-critical tasks.
method CARL combines model-based RL and cautious adaptation.
result CARL achieves higher rewards with fewer failures in safety-critical tasks.
The paper studies how neural policies can be interpreted using decision trees.
problem Understanding how machine learning controllers make decisions in complex environments.
method The approach involves disentangled representation using decision trees to interpret neural policies.
result The paper shows that disentanglement of learned neural dynamics improves interpretability.
Robots gather information resiliently despite failures and attacks.
problem Resilient information gathering in adversarial or failure-prone environments.
method First scalable algorithm for minimal communication, system-wide resiliency, and provable approximation performance.
result Algorithm ensures optimal or near-optimal solutions for any number of failures and attacks.
Paper proposes a deep RL algorithm that can learn from forbidden actions.
problem Learning from forbidden actions in constrained environments.
method Enhanced DQN with safety loss for learning from unsafe actions.
result Reduces hit constraints and accelerates convergence in experiments.
Safe active learning for multi-output Gaussian processes reduces data acquisition costs and ensures safety.
problem Expensive data acquisition and safety concerns in multi-output regression problems.
method Proposes a safe active learning approach considering data informativeness and safety constraints.
result Improved convergence compared to competitors on simulated and real-world datasets.
Tackles bridging machine learning and control theory for safety-critical systems.
problem Ensuring reliability and safety in machine learning applications for safety-critical systems.
method Review of recent advances in learning and control theory, historical context.
result Importance of control theorists joining the conversation on learning-related problems.
StageOpt efficiently optimizes safe decisions by separating safety and utility stages.
problem Optimizing unknown utility with safety constraints in sequential decisions.
method Develops StageOpt, a two-stage safe Bayesian optimization algorithm.
result StageOpt is more efficient and applicable to broader problems than existing methods.
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.
In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…
Safe Bayesian Optimization algorithms are improved to ensure safety in real-world applications.
problem Ensuring safety in Bayesian Optimization algorithms for real-world applications.
method Investigated and improved three safety-related issues of SafeOpt-type algorithms: frequentist uncertainty bounds, RKHS norm assumptions, and discrete search spaces.
result Introduced Real-{eta}-SafeOpt, Lipschitz-only Safe Bayesian Optimization (LoSBO), and Lipschitz-only GP-UCB (LoS-GP-UCB) algorithms that retain safety guarantees and superior performance.
Safe-EF improves federated learning for non-smooth, constrained optimization.
problem Federated learning's communication bottlenecks with high-dimensional model updates.
method Error feedback (EF) for non-smooth convex optimization with safety constraints.
result Safe-EF matches lower complexity bounds and ensures safety constraints.
Safe RL approach using Lyapunov functions.
problem Concurrent optimization of performance and safety constraints in RL.
method Lyapunov-based approach for CMDPs, transforming DP and RL algorithms.
result Significant performance improvement in balancing constraints and performance.
A language for specifying complex reinforcement learning tasks.
problem Challenges in specifying and shaping reward functions for complex reinforcement learning tasks.
method Proposes a new language and algorithm for automatically generating and shaping reward functions.
result SPECTRL tool outperforms state-of-the-art baselines.
Safe RL with binary feedback using SABRE algorithm.
problem Safe reinforcement learning with binary safety feedback.
method SABRE algorithm, combining active learning and reinforcement learning.
result Provable safe policy with high probability, no unsafe actions during training.
Safe Bayesian optimization tackles safety constraints in control engineering.
problem Handling safety constraints in parameter tuning of control systems.
method Lipschitz-only Safe Bayesian Optimization (LoSBO) and LoS-GP-UCB.
result SafeBO algorithms can violate safety constraints due to unreliable uncertainty bounds.
The paper addresses uncalibrated uncertainty estimates for object localization.
problem Uncalibrated uncertainty estimates for object localization in safety-critical applications.
method Adapting a technique for calibrating regression models to object localization.
result Calibrated model provides more reliable uncertainty estimates.
New metric predicts neural network reliability under novel conditions.
problem Verifying neural networks' safety in novel scenarios.
method ML Dependability metric, Task Undependability, Harmful Undependability.
result Accurately predicts reliability under novel conditions.
Enhances demonstrations with safety specifications using LTL.
problem Learning from demonstrations without safety specifications.
method Converts LTL specifications into a differentiable loss for training.
result System learns dynamic movement primitives that satisfy complex specifications.
Improved reinforcement learning for robotics with active uncertainty reduction.
problem Infeasibility of model-free reinforcement learning methods in robotics due to safety and time constraints.
method Active uncertainty reduction-based virtual environments with adaptive sampling for metric self-improvement.
result Better modeling capacity for complex system dynamics compared to established methods.
CalNF models rare failures with limited data, improving safety in autonomous systems.
problem Challenges in modeling and debugging rare safety-critical failures due to limited data.
method CalNF, a self-regularized framework for posterior learning from limited data.
result Achieves state-of-the-art performance on data-limited failure modeling and inverse problems.
A method uses a supervisor policy to train a new policy safely and quickly for robots.
problem Training a new control policy safely and quickly for robots.
method Weighted average of supervisor and learned policies, pioneer network to compensate.
result Demonstrated effectiveness in OpenAI Gym experiments.
Safe exploration method for RL under disturbance ensures safety with probabilistic guarantees.
problem Safe reinforcement learning in real environments with disturbance.
method Uses partial prior knowledge and conservative inputs to ensure state constraint satisfaction.
result Guaranteed safety with pre-specified probability in the presence of stochastic disturbance.
A new particle filter avoids resampling to improve state estimation in high dimensions.
problem Particle deprivation in high-dimensional state spaces.
method A resampling-free particle filter designed to mitigate particle deprivation.
result The filter offers a near-accurate representation of the posterior distribution in high-dimensional contexts.
Monotonicity helps in safely optimizing unknown functions.
problem Sequentially maximizing an unknown function with safety constraints.
method Gaussian process with monotonicity assumption, inspired by GP-UCB and SafeOpt.
result The proposed M-SafeUCB algorithm achieves theoretical guarantees and safety.
Paper derives uniform error bounds for Gaussian process regression for safer control applications.
problem Quantifying model error in Gaussian process regression for safety-critical applications.
method Employing Gaussian process distribution and continuity arguments, derive uniform error bounds under weaker assumptions.
result Derives novel uniform error bounds for Gaussian process regression under weaker assumptions.
APDO optimizes CMDPs with off-policy dual updates for faster convergence.
problem Learning policies that maximize long-term reward while satisfying safety constraints.
method Accelerated Primal-Dual Optimization (APDO) incorporating off-policy dual updates.
result APDO achieves better sample efficiency and faster convergence than existing methods.
Diverging Flows detects extrapolations in flow models, ensuring reliable predictions.
problem Flow models extrapolate into invalid data, leading to silent failures.
method Structurally enforce inefficient transport for off-manifold inputs.
result Effective detection of extrapolations without compromising predictive fidelity or inference latency.
Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured urban roadways. Since there are many possible scenarios, manually tackling all po…
Quantized BNNs maintain uncertainty estimation quality despite reduced precision.
problem Reduced precision in BNNs due to quantization.
method Quantized BNNs with 32-bit weights and activations compressed to 16-bit integers.
result Uniform quantization does not significantly degrade uncertainty estimation quality.
FSPT identifies training space to prevent ML model extrapolation.
problem Lack of training data leads to unreliable predictions outside the training space.
method FSPT: Feature Space Partitioning Tree to identify training space.
result Strong relationship between model performance and FSPT score.
New method detects dangerous states in gridworlds using geometric defects.
problem Detecting dangerous states in gridworlds for AI safety.
method Modified state complexes and Gromov's Link Condition.
result Geometric defects indicate dangerous states in gridworlds.
Algorithm ensures safe optimization under unknown constraints.
problem Optimization under unknown safety constraints.
method Reliable Frank-Wolfe (Reliable-FW) algorithm for non-convex functions.
result Algorithm finds approximate first-order stationary points safely.
New algorithm reduces sample complexity for safe reinforcement learning.
problem Safe reinforcement learning in constrained MDPs with performance and safety constraints.
method Model-based primal-dual algorithm balancing regret and bounded constraint violations.
result Proves near-optimal policies with bounded violations or zero violations in CMDPs.