{"id":31021548,"url":"https://github.com/sisl/interpretableselfawareprediction","last_synced_at":"2026-03-16T16:08:17.044Z","repository":{"id":63484654,"uuid":"495258285","full_name":"sisl/InterpretableSelfAwarePrediction","owner":"sisl","description":null,"archived":false,"fork":false,"pushed_at":"2022-12-16T00:15:03.000Z","size":40,"stargazers_count":15,"open_issues_count":1,"forks_count":1,"subscribers_count":8,"default_branch":"main","last_synced_at":"2024-03-24T17:10:24.040Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/sisl.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-05-23T04:31:12.000Z","updated_at":"2024-03-18T12:51:28.000Z","dependencies_parsed_at":"2023-01-29T06:15:34.729Z","dependency_job_id":null,"html_url":"https://github.com/sisl/InterpretableSelfAwarePrediction","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sisl/InterpretableSelfAwarePrediction","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2FInterpretableSelfAwarePrediction","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2FInterpretableSelfAwarePrediction/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2FInterpretableSelfAwarePrediction/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2FInterpretableSelfAwarePrediction/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sisl","download_url":"https://codeload.github.com/sisl/InterpretableSelfAwarePrediction/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sisl%2FInterpretableSelfAwarePrediction/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274955964,"owners_count":25380669,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-13T02:00:10.085Z","response_time":70,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-09-13T11:23:36.353Z","updated_at":"2026-03-16T16:08:12.017Z","avatar_url":"https://github.com/sisl.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Interpretable Self-Aware Prediction (ISAP)\n\nWe propose the use of evidential deep learning to perform one-shot epistemic uncertainty estimation over a low-dimensional, interpretable latent space in a trajectory prediction setting. This code runs the qualitative and quantitative experiments to validate the proposed Interpretable Self-Aware Prediction (ISAP) framework. \n\nSee our [paper](https://arxiv.org/abs/2211.08701) for more details:\n\nM. Itkina and M. J. Kochenderfer. \"Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction\". In Conference on Robot Learning (CoRL), 2022. \n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://user-images.githubusercontent.com/24766091/207967821-429d7b98-a3b3-4ff4-9ebf-f0280649d001.gif\" width=\"500\"\u003e \n\u003cimg src=\"https://user-images.githubusercontent.com/24766091/207967836-6f6ad463-90ff-4a17-9aa3-ccb3f89211c6.gif\" width=\"500\"\u003e\n\u003c/p\u003e\nQualitative results for our ISAP framework on in-distribution (ID) and out-of-distribution (OOD) examples for the input trajectory experiment. We see that the ID example (left) has a slower moving agent of interest (red history boxes closer together) than the OOD example. Thus, ISAP learns the epistemic uncertainty in the agent behavior latent variable to be higher (α0,agent is lower) for the OOD case than the ID case. \n\n## Instructions\n\nThe required dependencies are listed in `dependencies.txt`.\n\nThe NuScenes trajectory prediction dataset has to be downloaded from: https://www.nuscenes.org/nuscenes#download and placed into the `data/nuscenes/` folder, including a `covernet_traj_set` containing the trajectory sets, `maps` directory, and `v1.0-trainval` data. The NuScenes github repository: https://github.com/nutonomy/nuscenes-devkit should be cloned and the `nuscenes-devkit` folder to be placed at the top-level.\n\nThe PostNet code should be cloned from: https://github.com/sharpenb/Posterior-Network and placed at the top-level.\n\nThis code was developed and tested with `Python 3.6.12`.\n\nTo replicate the input trajectory speed experiments, please run the following files: \n\n``run_isap_agent_speed.sh``\n\n``run_postcovernet_agent_speed.sh``\n\n``run_ensembles_agent_speed.sh``\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsisl%2Finterpretableselfawareprediction","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsisl%2Finterpretableselfawareprediction","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsisl%2Finterpretableselfawareprediction/lists"}