16 papers
Belief-Informed Hybrid Control with Almost-Sure Target-Set Convergence
Clinton Enwerem, Saleh Kemal, John S. Baras +1
Controlling a hybrid system to a target set under parameter uncertainty can require informative actions that temporarily drive the system state away from the specified set. We prop…
Differentiable Ternary Temporal Logic Semantics with Polynomial Surrogate Networks
Ryan Matheu, Sai Sandeep Damera, John S. Baras +1
Temporal logic provides designers a formal reasoning tool for specifying complex spatio-temporal behaviors and tasks for autonomous systems. Many techniques exist for control synth…
Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds
Clinton Enwerem, John S. Baras, Calin Belta
Dexterous manipulation policies learned by imitation are typically evaluated for robustness to variation in scenes, objects, or instructions, but their performance across task exec…
Grasp Execution Without a Planner: Configuration-Space Grasp Distance Fields with Certified Safety & Guaranteed Quality
Clinton Enwerem, John S. Baras, Calin Belta
Mainstream plan-then-track approaches to multifingered grasp execution entail selecting a grasp, planning a collision-free trajectory, and tracking the resulting trajectory via a f…
FIRMGrasp: A Friction-Informed Risk Margin for Robust Grasp Synthesis
Clinton Enwerem, John S. Baras, Calin Belta
Classical grasp quality metrics assume one deterministic friction coefficient and therefore cannot assess whether a grasp maintains force closure across plausible friction values.…
EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows
Clinton Enwerem, John S. Baras, Calin Belta
Most learned dexterous grasp generators relegate contact forces to a downstream verification step, so a kinematically-plausible pose can still violate the conditions for a stable p…
IDDMBSE: Integrating Data-Driven and Model-Based Systems Engineering for Trusted Autonomous Cyber-Physical Systems
John S. Baras, Sai Sandeep Damera, Ryan Matheu +2
Autonomous cyber-physical systems (CPS) sit at the intersection of Model-Based Systems Engineering (MBSE) and data-driven Machine Learning and Artificial Intelligence (ML/AI), yet…
On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate Networks
Sai Sandeep Damera, Ryan Matheu, Aniruddh G. Puranic +2
Recurrent Neural Networks (RNNs) can learn to predict Signal Temporal Logic (STL) verdicts online from partial trajectories, but deploying them as runtime monitors in safety-critic…
Ternary Logic Encodings of Temporal Behavior Trees with Application to Control Synthesis
Ryan Matheu, John S. Baras, Calin Belta
Behavior Trees (BTs) provide designers with an intuitive graphical interface to construct long-horizon plans for autonomous systems. To ensure their correctness and safety, rigorou…
Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair
Aniruddh G. Puranic, Sebastian Schirmer, John S. Baras +1
Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect, posing significant challenges fo…
Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertainty
Clinton Enwerem, Shreya Kalyanaraman, John S. Baras +1
Contact variability, sensing uncertainty, and external disturbances make grasp execution stochastic. Expected-quality objectives ignore tail outcomes and often select grasps that f…
Risk-Constrained Belief-Space Optimization for Safe Control under Latent Uncertainty
Clinton Enwerem, John S. Baras, Calin Belta
Many safety-critical control systems operate under latent uncertainty that sensors cannot resolve at decision time. Such uncertainty, arising from unknown physical properties, dist…
Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regression
Clinton Enwerem, Aniruddh G. Puranic, John S. Baras +1
Mainstream approximate action-value iteration reinforcement learning (RL) algorithms suffer from overestimation bias, leading to suboptimal policies in high-variance stochastic env…
Robust Stochastic Shortest-Path Planning via Risk-Sensitive Incremental Sampling
Clinton Enwerem, Erfaun Noorani, John S. Baras +1
With the pervasiveness of Stochastic Shortest-Path (SSP) problems in high-risk industries, such as last-mile autonomous delivery and supply chain management, robust planning algori…
Time-Robust Path Planning with Piece-Wise Linear Trajectory for Signal Temporal Logic Specifications
Nhan-Khanh Le, Erfaun Noorani, Sandra Hirche +1
Real-world scenarios are characterized by timing uncertainties, e.g., delays, and disturbances. Algorithms with temporal robustness are crucial in guaranteeing the successful execu…
Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis
Rui Liu, Anish Gupta, Erfaun Noorani +1
Reinforcement Learning (RL) has shown exceptional performance across various applications, enabling autonomous agents to learn optimal policies through interaction with their envir…