Chris Agia

I am a 4th-year PhD student in Computer Science at Stanford University advised by Jeannette Bohg and Marco Pavone. I'm a member of the Stanford Artificial Intelligence Laboratory, the Center for Research on Foundation Models, and work jointly with the Interactive Perception and Robot Learning Lab and the Autonomous Systems Lab.

My research is structured around the following core thrusts:

1. Endowing robots with the ability to plan for a wide range of tasks;
2. Increasing the reliability of AI-driven robots during deployment;
3. Establishing connections between model behavior and data;
4. Facilitating effective interaction between robots and humans.

I set aside weekly time for research discussion and mentorship. If you feel this could be of benefit, please book an open slot here.

I'm also a Clear Ventures Deeptech Fellow interested in startups. Beyond research, I enjoy sports (Stanford Club Men's Soccer) and music!

cagia[at]cs.stanford.edu  /  CV  /  LinkedIn  /  GitHub  /  Scholar

How can we plan to solve unseen, long-horizon tasks from a single, partial-view point cloud of the scene, and how can we do so without access to long-horizon training data? Points2Plans leverages transformer-based relational dynamics to learn the symbolic and geometric effects of robot skills, then compose the skills at test time to generate a long-horizon symbolic and geometric plan.

Pretrained large language models can be readily used to obtain high-level robot plans from natural lanugage instructions, but should these plans be executed without verifying them on the geometric-level? We propose Text2Motion, a language-based planner that tests if LLM-generated plans (a) satisfy user instructions and (b) are geometric feasibility prior to executing them.

System-level failures are not due to failures of any individual component of the autonomy stack but system-level deficiencies in semantic reasoning. Such edge cases, dubbed semantic anomalies, are simple for a human to disentangle yet require insightful reasoning. We introduce a runtime monitor based on large language models to recognize failure-inducing semantic anomalies.

How can semantic information be leveraged to improve localization accuracy in changing environments? We present a robust LiDAR-based localization algorithm that exploits both semantic and geometric properties of the scene with an adaptive fusion strategy.

Deep Reinforcement Learning is effective for learning robot navigation policies in rough terrain and cluttered simulated environments. In this work, we introduce a series of techniques that are applied in the policy learning phase to enhance transferability to real-world domains.

Robot behavior policies trained via imitation learning are prone to failure under conditions that deviate from their training data. In this work, we present Sentinel, a runtime monitor that detects unknown failures (requiring no data of failures) of generative robot policies at deployment time.

How can we integrate human preferences into robot plans in a zero-shot manner, i.e., without requiring tens of thousands of data points of human feedback? We propose Text2Interaction, a planning framework that invokes large language models to generate a task plan, motion preferences as Python code, and parameters of a safe controller.

How can we mitigate the computational expense and latency of LLMs for real-time anomaly detection and reactive planning? We propose a two-stage reasoning framework, whereby fast a LLM embedding model flags potential observational anomalies while a slower generative LLM assesses the safety-criticality of flagged anomalies and selects a safety-preserving fallback plan.

We introduce DROID (Distributed Robot Interaction Dataset), a diverse robot manipulation dataset with 76k demonstration trajectories (or 350 hours of interaction data), collected across 564 scenes and 86 tasks by 50 data collectors in North America, Asia, and Europe over the course of 12 months. We demonstrate that training with DROID leads to policies with higher performance and improved generalization ability.

Future space exploration missions to unknown worlds will require robust reasoning, planning, and decision-making capabilities, enabled by the right choice of onboard models. In this work, we aim to understand what onboard models a spacecraft needs for fully autonomous space exploration.

Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train “generalist” X-robot policy that can be adapted efficiently to new robots, tasks, and environments?

Solving sequential manipulation tasks requires coordinating geometric dependencies between actions. We develop a scalable framework for training skills independently, and then combine the skills at planning time to solve unseen long-horizon tasks. Planning is formulated as a maximization problem over the expected success of the skill sequence, which we demonstrate is well-approximated by the product of Q-values.

3D Scene Graphs (3DSGs) are informative abstractions of our world that unify symbolic, semantic, and metric scene representations. We present a benchmark for robot task planning over large 3DSGs and evaluate classical and learning-based planners; showing that real-time planning requires 3DSGs and planners to be jointly adapted to better exploit 3DSG hierarchies.

Pretraining visual representations for robotic reinforcement learning can improve sample efficiency and policy performance. In this paper, we take an alternate approach and propose to augment the state embeddings of a self-driving agent with attention in the latent space, accelerating the convergence of Actor-Critic algorithms.

Small-scale semantic reconstruction methods have had little success in large outdoor scenes as a result of exponential increases in sparsity, and a computationally expensive design. We propose a sparse convolutional network architecture based on the Minkowski Engine, achieving state-of-the-art results for semantic scene completion in 2D/3D space from LiDAR point clouds.

Direct methods are able to track motion with considerable long-term accuracy. However, scale inconsistent estimates arise from random or unit depth initialization. We integrate dense depth prediction with the Direct Sparse Odometry system to accelerate convergence in the windowed bundle-adjustment and promote estimates with consistent scale.

We evaluate the suitability of existing simulators for research at the intersection of task planning and 3D scene graphs and construct a benchmark for comparison of symbolic planners. Furthermore, we explore the use of Graph Neural Networks to harness invariances in the relational structure of planning domains and learn representations that afford faster planning.

Several components of my industry research projects were patented alongside submitting to conference / journal venues.

Relates to processing point clouds for autonomous driving of a vehicle. More specifically, relates to processing a sequence of point clouds to generate a birds-eye-view (BEV) image of an environment of the vehicle which includes pixels associated with road surface labels.

Relates to methods and systems for generating semantically completed 3D data from sparse 3D data such as point clouds.