MIT Aerospace Controls Laboratory ORG

3D Trajectory Planner in Unknown Environments

ROS package for dynamic obstacle avoidance for ground robots trained with deep RL

Trajectory Planner in Multi-Agent and Dynamic Environments

No description.

A GPU implementation of Model Predictive Path Integral (MPPI) control that uses a probabilistic traversability model for planning risk-aware trajectories.

[RSS 2025] ROMAN: a view-invariant global localization method that matches objects from different robot views for reliable pose estimation even when a scene is observed from opposite views

graph-theoretic framework for robust pairwise data association

No description.

Perception-Aware Trajectory Planner in Dynamic Environments

Distributed Pose Graph Optimization

Training code for GA3C-CADRL algorithm (collision avoidance with deep RL)

Decentralized Multiagent Trajectory Planner Robust to Communication Delay

ROS1/2 wrapper for ROMAN, a view-invariant global localization method

No description.

Simplexes with Minimum Volume Enclosing Polynomial Curves

SANDO: Safe Autonomous Trajectory Planning for Dynamic Unknown Environments

MIT ACL distributed formation flying using multirotors

No description.

ROS wrapper for distributed pose graph optimization

PUMA: Fully Decentralized Uncertainty-aware Multiagent Trajectory Planner with Real-time Image Segmentation-based Frame Alignment

List of planning algorithms developed at MIT-ACL

CLEAR algorithm for multi-view data association

Android app to enable ROS on a Loomo robot

[ICRA 2025] TCAFF: a multiple hypothesis algorithm for aligning coordinate frames of collaborative robots

ROS wrapper for FastSAM, with docker

No description.

Meridian is package for localizing a ground robot from aerial ortho-imagery, providing meter-level pose estimates without any initial pose information or environmental fine-tuning.

No description.

No description.

Optimal Reciprocal Collision Avoidance, Python bindings

Linear separability (via planes) of two sets of 3D points

Implementation of several multiagent trajectory generation algorithms

ROS wrapper for YOLOv7, with docker

Planning Beyond the Sensing Horizon Using a Learned Context

Deep Cost-to-Go Planning Algorithm (IROS '19)

Trajectory generation and simulation for multi-agent swarm

Microsoft AirSim with ACL snap-stack autopilot integration

No description.

No description.

Iterative sequential convex programming path planner, from Steven and Mark's ICRA 2015 paper

Repo for robust training of NN controllers with verification tools

Båtvik seasonal dataset loader

MIT 16.06 Spring 2026

No description.

No description.

An optimization-based multi-sensor state estimator

ROS packages for simulating multiple Jackals in Gazebo

No description.

Git repo for the paper "Online Data-Driven Safety Certification for Systems Subject to Unknown Disturbances"

Multimodal data association

ROS drivers for OptiTrack Motive 2 motion capture system

Optimal Reciprocal Collision Avoidance in Three Dimensions (C++)

No description.

No description.

No description.

Unified Signals_and_Systems (16.002) - Fall 2026

Hamilton-Jacobi reachability analysis infused with neural network verification

No description.

ROS wrapper for MOTLEE

A ROS wrapper for trajectory planning based on motion primitives

Re-publishing Loomo topics for FASTER

A library for flexible voxel-based mapping, mainly focusing on truncated and Euclidean signed distance fields.

snap_vio wraps mvVISLAM from the machine vision library, providing a ROS interface.

CMake toolchain and rules for building apps for Hexagon DSP and apps processor on Qualcomm SoCs