Search Results for author:
Found 9 papers, 4 papers with code
Dialogue-based generation of self-driving simulation scenarios using Large Language Models
Simulation is an invaluable tool for developing and evaluating controllers for self-driving cars.
Testing Rare Downstream Safety Violations via Upstream Adaptive Sampling of Perception Error Models
Testing black-box perceptual-control systems in simulation faces two difficulties.
Risk-Driven Design of Perception Systems
We formulate a risk function to quantify the effect of a given perceptual error on overall safety, and show how we can use it to design safer perception systems by including a risk-dependent term in the loss function and generating training data in risk-sensitive regions.
Learning physics-informed simulation models for soft robotic manipulation: A case study with dielectric elastomer actuators
We simulate the task of using DEA to pull a coin along a surface with frictional contact, using FEM, and evaluate the physics-informed model for simulation, control, and inference.
Robust Learning from Observation with Model Misspecification
Imitation learning (IL) is a popular paradigm for training policies in robotic systems when specifying the reward function is difficult.
Learning rewards for robotic ultrasound scanning using probabilistic temporal ranking
This work considers the inverse problem, where the goal of the task is unknown, and a reward function needs to be inferred from exploratory example demonstrations provided by a demonstrator, for use in a downstream informative path-planning policy.
Elaborating on Learned Demonstrations with Temporal Logic Specifications
We also implement our system on a PR-2 robot to show how a demonstrator can start with an initial (sub-optimal) demonstration, then interactively improve task success by including additional specifications enforced with our differentiable LTL loss.
Learning Factored Markov Decision Processes with Unawareness
Methods for learning and planning in sequential decision problems often assume the learner is aware of all possible states and actions in advance.
Reasoning about Unforeseen Possibilities During Policy Learning
Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning.
